Search

Software systems often record important runtime information in logs to help with troubleshooting. Log-based anomaly detection has become a key research area that aims to identify system issues through log data, ultimately enhancing the reliability of software systems. Traditional deep learning methods often struggle to capture the semantic information embedded in log data, which is typically organized in natural language. In this paper, we propose LogLLM, a log-based anomaly detection framework that leverages large language models (LLMs). LogLLM employs BERT for extracting semantic vectors from log messages, while utilizing Llama, a transformer decoder-based model, for classifying log sequences. Additionally, we introduce a projector to align the vector representation spaces of BERT and Llama, ensuring a cohesive understanding of log semantics. Unlike conventional methods that require log parsers to extract templates, LogLLM preprocesses log messages with regular expressions, streamlining the entire process. Our framework is trained through a novel three-stage procedure designed to enhance performance and adaptability. Experimental results across four public datasets demonstrate that LogLLM outperforms state-of-the-art methods. Even when handling unstable logs, it effectively captures the semantic meaning of log messages and detects anomalies accurately.

Data and model heterogeneity are two core issues in Heterogeneous Federated Learning (HtFL). In scenarios with heterogeneous model architectures, aggregating model parameters becomes infeasible, leading to the use of prototypes (i.e., class representative feature vectors) for aggregation and guidance. However, they still experience a mismatch between the extra guiding objective and the client's original local objective when aligned with global prototypes. Thus, we propose a Federated Learning-to-Guide (FedL2G) method that adaptively learns to guide local training in a federated manner and ensures the extra guidance is beneficial to clients' original tasks. With theoretical guarantees, FedL2G efficiently implements the learning-to-guide process using only first-order derivatives w.r.t. model parameters and achieves a non-convex convergence rate of O(1/T). We conduct extensive experiments on two data heterogeneity and six model heterogeneity settings using 14 heterogeneous model architectures (e.g., CNNs and ViTs) to demonstrate FedL2G's superior performance compared to six counterparts.

Mathematical optimization is ubiquitous in modern applications. However, in practice, we often need to use nonlinear optimization models, for which the existing optimization tools such as Cplex or Gurobi may not be directly applicable and an (error-prone) manual transformation often has to be done. Thus, to address this issue, in this paper we investigate the problem of automatically verifying and synthesizing reductions, the solution of which may allow an automatic linearization of nonlinear models. We show that the synthesis of reductions can be formulated as an $\exists^* \forall^*$ synthesis problem, which can be solved by an SMT solver via the counter-example guided inductive synthesis approach (CEGIS)., Comment: 4 pages, conference

A non-extensive (3+1)-dimensional hydrodynamic model for multi-particle production processes, NEX-CLVisc, is developed in the framework of CLVisc where the viscous corrections are turned off. It assumes that the non-extensive effects consistently exist in the initial conditions set by the optical Glauber model, the equation of state and the hadron kinetic freeze-out procedure. The model is then applied to simulate the pseudo-rapidity ($\eta$) distribution, the transverse momentum ($p_{\rm T}$) spectra and the $p_{\rm T}$-differential elliptic flow ($v_2$) of charged particles in Pb-Pb collisions at $\sqrt{s_{\rm NN}}=$ 2.76 TeV and 5.02 TeV, respectively. It is found that the model can reasonably well reproduce the experimental data of the $\eta$ distribution and the charged-particle spectra in a $p_{\rm T}$ range up to 6-8 GeV/c. When compared with the ideal hydrodynamic model, the $p_{\rm T}$-differential $v_2$ of charged particles is suppressed in the NEX-CLVisc model, which is similar to that observed in the hydrodynamic model with a shear viscous correction. Moreover, due to the lack of the viscous corrections and the event-by-event fluctuation, the model can only describe the $p_{\rm T}$-differential $v_2$ up to 3-4 GeV/c, which is smaller than its applicable range for the particle $p_{\rm T}$ spectra., Comment: 9 pages, 4 figures, 4 tables. Revised accroding to the referee's comments

Inspired by the BESIII newest observation of X(2370) glueball-like particle, we search its productions in both $e^+e^-$ collisions at $\sqrt{s}=$ 4.95 GeV and proton-proton (pp) collisions at $\sqrt{s}=$ 13 TeV with a parton and hadron cascade model PACIAE. In this model, the final partonic state (FPS) and the final hadronic state (FHS) are consecutively simulated and recorded. The X(2370) glueball- or tetraquark-state is then, respectively, recombined by two gluons or four quarks $ss\bar{s}\bar{s}$ in the FPS using the quantum statistical mechanics inspired dynamically constrained phase-space coalescence (DCPC) model. The X(2370) molecular-state is recombined by the baryon-antibaryon of $\Lambda$-$\bar{\Lambda}$ or $\Sigma$-$\bar{\Sigma}$, or by three mesons of $\pi^+\pi^{-}\eta'$, $K^+K^-\eta'$, or $K_S^0K_S^0\eta'$ in the FHS using DCPC model. In both $e^+e^-$ and pp collisions, significant discrepancies in the yields, the transverse momentum spectra and the rapidity distributions among the X(2370) glueball-, tetraquark-, and molecular-state are observed. These discrepancies are proposed as valuable criteria identifying the X(2370) different states from each other. Our results not only support the BESIII observation of glueball-like particle $\rm X(2370)$ production in $e^+e^-$ collisions, but also serve as a prediction for the $\rm X(2370)$ production in pp collisions. We strongly suggest the experimental measurement of the X(2370) glueball-like particle production in pp collisions at the LHC energies., Comment: 6 pages, 5 figures

Virtual Try-On (VTON) has become a transformative technology, empowering users to experiment with fashion without ever having to physically try on clothing. However, existing methods often struggle with generating high-fidelity and detail-consistent results. While diffusion models, such as Stable Diffusion series, have shown their capability in creating high-quality and photorealistic images, they encounter formidable challenges in conditional generation scenarios like VTON. Specifically, these models struggle to maintain a balance between control and consistency when generating images for virtual clothing trials. OutfitAnyone addresses these limitations by leveraging a two-stream conditional diffusion model, enabling it to adeptly handle garment deformation for more lifelike results. It distinguishes itself with scalability-modulating factors such as pose, body shape and broad applicability, extending from anime to in-the-wild images. OutfitAnyone's performance in diverse scenarios underscores its utility and readiness for real-world deployment. For more details and animated results, please see \url{https://humanaigc.github.io/outfit-anyone/}., Comment: 10 pages, 13 figures

Co-locating latency-critical services (LCSs) and best-effort jobs (BEJs) constitute the principal approach for enhancing resource utilization in production. Nevertheless, the co-location practice hurts the performance of LCSs due to resource competition, even when employing isolation technology. Through an extensive analysis of voluminous real trace data derived from two production clusters, we observe that BEJs typically exhibit periodic execution patterns and serve as the primary sources of interference to LCSs. Furthermore, despite occupying the same level of resource consumption, the diverse compositions of BEJs can result in varying degrees of interference on LCSs. Subsequently, we propose PISM, a proactive Performance Interference Scoring and Mitigating framework for LCSs through the optimization of BEJ scheduling. Firstly, PISM adopts a data-driven approach to establish a characterization and classification methodology for BEJs. Secondly, PISM models the relationship between the composition of BEJs on servers and the response time (RT) of LCSs. Thirdly, PISM establishes an interference scoring mechanism in terms of RT, which serves as the foundation for BEJ scheduling. We assess the effectiveness of PISM on a small-scale cluster and through extensive data-driven simulations. The experiment results demonstrate that PISM can reduce cluster interference by up to 41.5%, and improve the throughput of long-tail LCSs by 76.4%.

We propose a linear-complexity method for sampling from truncated multivariate normal (TMVN) distributions with high fidelity by applying nearest-neighbor approximations to a product-of-conditionals decomposition of the TMVN density. To make the sequential sampling based on the decomposition feasible, we introduce a novel method that avoids the intractable high-dimensional TMVN distribution by sampling sequentially from $m$-dimensional TMVN distributions, where $m$ is a tuning parameter controlling the fidelity. This allows us to overcome the existing methods' crucial problem of rapidly decreasing acceptance rates for increasing dimension. Throughout our experiments with up to tens of thousands of dimensions, we can produce high-fidelity samples with $m$ in the dozens, achieving superior scalability compared to existing state-of-the-art methods. We study a tetrachloroethylene concentration dataset that has $3{,}971$ observed responses and $20{,}730$ undetected responses, together modeled as a partially censored Gaussian process, where our method enables posterior inference for the censored responses through sampling a $20{,}730$-dimensional TMVN distribution.

Detecting anomalies in business processes is crucial for ensuring operational success. While many existing methods rely on statistical frequency to detect anomalies, it's important to note that infrequent behavior doesn't necessarily imply undesirability. To address this challenge, detecting anomalies from a semantic viewpoint proves to be a more effective approach. However, current semantic anomaly detection methods treat a trace (i.e., process instance) as multiple event pairs, disrupting long-distance dependencies. In this paper, we introduce DABL, a novel approach for detecting semantic anomalies in business processes using large language models (LLMs). We collect 143,137 real-world process models from various domains. By generating normal traces through the playout of these process models and simulating both ordering and exclusion anomalies, we fine-tune Llama 2 using the resulting log. Through extensive experiments, we demonstrate that DABL surpasses existing state-of-the-art semantic anomaly detection methods in terms of both generalization ability and learning of given processes. Users can directly apply DABL to detect semantic anomalies in their own datasets without the need for additional training. Furthermore, DABL offers the capability to interpret the causes of anomalies in natural language, providing valuable insights into the detected anomalies.

An effective auto-scaling framework is essential for microservices to ensure performance stability and resource efficiency under dynamic workloads. As revealed by many prior studies, the key to efficient auto-scaling lies in accurately learning performance patterns, i.e., the relationship between performance metrics and workloads in data-driven schemes. However, we notice that there are two significant challenges in characterizing performance patterns for large-scale microservices. Firstly, diverse microservices demonstrate varying sensitivities to heterogeneous machines, causing difficulty in quantifying the performance difference in a fixed manner. Secondly, frequent version upgrades of microservices result in uncertain changes in performance patterns, known as pattern drifts, leading to imprecise resource capacity estimation issues. To address these challenges, we propose Humas, a heterogeneity- and upgrade-aware auto-scaling framework for large-scale microservices. Firstly, Humas quantifies the difference in resource efficiency among heterogeneous machines for various microservices online and normalizes their resources in standard units. Additionally, Humas develops a least squares density-difference (LSDD) based algorithm to identify pattern drifts caused by upgrades. Lastly, Humas generates capacity adjustment plans for microservices based on the latest performance patterns and predicted workloads. The experiment results conducted on 50 real microservices with over 11,000 containers demonstrate that Humas improves resource efficiency and performance stability by approximately 30.4% and 48.0%, respectively, compared to state-of-the-art approaches., Comment: 14 pages; 27 figures

Addressing the statistical challenge of computing the multivariate normal (MVN) probability in high dimensions holds significant potential for enhancing various applications. One common way to compute high-dimensional MVN probabilities is the Separation-of-Variables (SOV) algorithm. This algorithm is known for its high computational complexity of O(n^3) and space complexity of O(n^2), mainly due to a Cholesky factorization operation for an n X n covariance matrix, where $n$ represents the dimensionality of the MVN problem. This work proposes a high-performance computing framework that allows scaling the SOV algorithm and, subsequently, the confidence region detection algorithm. The framework leverages parallel linear algebra algorithms with a task-based programming model to achieve performance scalability in computing process probabilities, especially on large-scale systems. In addition, we enhance our implementation by incorporating Tile Low-Rank (TLR) approximation techniques to reduce algorithmic complexity without compromising the necessary accuracy. To evaluate the performance and accuracy of our framework, we conduct assessments using simulated data and a wind speed dataset. Our proposed implementation effectively handles high-dimensional multivariate normal (MVN) probability computations on shared and distributed-memory systems using finite precision arithmetics and TLR approximation computation. Performance results show a significant speedup of up to 20X in solving the MVN problem using TLR approximation compared to the reference dense solution without sacrificing the application's accuracy. The qualitative results on synthetic and real datasets demonstrate how we maintain high accuracy in detecting confidence regions even when relying on TLR approximation to perform the underlying linear algebra operations.

Artificial intelligence (AI) has revolutionized software development, shifting from task-specific codes (Software 1.0) to neural network-based approaches (Software 2.0). However, applying this transition in engineering software presents challenges, including low surrogate model accuracy, the curse of dimensionality in inverse design, and rising complexity in physical simulations. We introduce an interpolating neural network (INN), grounded in interpolation theory and tensor decomposition, to realize Engineering Software 2.0 by advancing data training, partial differential equation solving, and parameter calibration. INN offers orders of magnitude fewer trainable/solvable parameters for comparable model accuracy than traditional multi-layer perceptron (MLP) or physics-informed neural networks (PINN). Demonstrated in metal additive manufacturing, INN rapidly constructs an accurate surrogate model of Laser Powder Bed Fusion (L-PBF) heat transfer simulation, achieving sub-10-micrometer resolution for a 10 mm path in under 15 minutes on a single GPU. This makes a transformative step forward across all domains essential to engineering software., Comment: 9 pages, 2 figures

With its elastic power and a pay-as-you-go cost model, the deployment of deep learning inference services (DLISs) on serverless platforms is emerging as a prevalent trend. However, the varying resource requirements of different layers in DL models hinder resource utilization and increase costs, when DLISs are deployed as a single function on serverless platforms. To tackle this problem, we propose a model partitioning framework called MOPAR. This work is based on the two resource usage patterns of DLISs: global differences and local similarity, due to the presence of resource dominant (RD) operators and layer stacking. Considering these patterns, MOPAR adopts a hybrid approach that initially divides the DL model vertically into multiple slices composed of similar layers to improve resource efficiency. Slices containing RD operators are further partitioned into multiple sub-slices, enabling parallel optimization to reduce inference latency. Moreover, MOPAR comprehensively employs data compression and share-memory techniques to offset the additional time introduced by communication between slices. We implement a prototype of MOPAR and evaluate its efficacy using four categories of 12 DL models on OpenFaaS and AWS Lambda. The experiment results show that MOPAR can improve the resource efficiency of DLISs by 27.62\% on average, while reducing latency by about 5.52\%. Furthermore, based on Lambda's pricing, the cost of running DLISs is reduced by about 2.58 $\times$ using MOPAR.

Heterogeneous Federated Learning (HtFL) enables task-specific knowledge sharing among clients with different model architectures while preserving privacy. Despite recent research progress, transferring knowledge in HtFL is still difficult due to data and model heterogeneity. To tackle this, we introduce a public pre-trained generator (e.g., StyleGAN or Stable Diffusion) as the bridge and propose a new upload-efficient knowledge transfer scheme called Federated Knowledge-Transfer-Loop (FedKTL). It can produce task-related prototypical image-vector pairs via the generator's inference on the server. With these pairs, each client can transfer common knowledge from the generator to its local model through an additional supervised local task. We conduct extensive experiments on four datasets under two types of data heterogeneity with 14 heterogeneous models, including CNNs and ViTs. Results show that our FedKTL surpasses seven state-of-the-art methods by up to 7.31%. Moreover, our knowledge transfer scheme is applicable in cloud-edge scenarios with only one edge client. Code: https://github.com/TsingZ0/FedKTL, Comment: Accepted by CVPR2024. We have incorporated additional analysis for the Stable Diffusion experiments in Appendix A

Laser-directed-energy deposition (DED) offers advantages in additive manufacturing (AM) for creating intricate geometries and material grading. Yet, challenges like material inconsistency and part variability remain, mainly due to its layer-wise fabrication. A key issue is heat accumulation during DED, which affects the material microstructure and properties. While closed-loop control methods for heat management are common in DED research, few integrate real-time monitoring, physics-based modeling, and control in a unified framework. Our work presents a digital twin (DT) framework for real-time predictive control of DED process parameters to meet specific design objectives. We develop a surrogate model using Long Short-Term Memory (LSTM)-based machine learning with Bayesian Inference to predict temperatures in DED parts. This model predicts future temperature states in real time. We also introduce Bayesian Optimization (BO) for Time Series Process Optimization (BOTSPO), based on traditional BO but featuring a unique time series process profile generator with reduced dimensions. BOTSPO dynamically optimizes processes, identifying optimal laser power profiles to attain desired mechanical properties. The established process trajectory guides online optimizations, aiming to enhance performance. This paper outlines the digital twin framework's components, promoting its integration into a comprehensive system for AM., Comment: 12 Pages, 10 Figures, 1 Table, NAMRC Conference

Recently, Heterogeneous Federated Learning (HtFL) has attracted attention due to its ability to support heterogeneous models and data. To reduce the high communication cost of transmitting model parameters, a major challenge in HtFL, prototype-based HtFL methods are proposed to solely share class representatives, a.k.a, prototypes, among heterogeneous clients while maintaining the privacy of clients' models. However, these prototypes are naively aggregated into global prototypes on the server using weighted averaging, resulting in suboptimal global knowledge which negatively impacts the performance of clients. To overcome this challenge, we introduce a novel HtFL approach called FedTGP, which leverages our Adaptive-margin-enhanced Contrastive Learning (ACL) to learn Trainable Global Prototypes (TGP) on the server. By incorporating ACL, our approach enhances prototype separability while preserving semantic meaning. Extensive experiments with twelve heterogeneous models demonstrate that our FedTGP surpasses state-of-the-art methods by up to 9.08% in accuracy while maintaining the communication and privacy advantages of prototype-based HtFL. Our code is available at https://github.com/TsingZ0/FedTGP., Comment: Accepted by AAAI2024

Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain. Whereas traditional FL (tFL) focuses on jointly learning a global model, pFL aims to achieve a balance between the global and personalized objectives of each client in FL settings. To foster the pFL research community, we propose PFLlib, a comprehensive pFL algorithm library with an integrated evaluation platform. In PFLlib, We implement 34 state-of-the-art FL algorithms (including 7 classic tFL algorithms and 27 pFL algorithms) and provide various evaluation environments with three statistically heterogeneous scenarios and 14 datasets. At present, PFLlib has already gained 850 stars and 199 forks on GitHub.

Multivariate normal (MVN) probabilities arise in myriad applications, but they are analytically intractable and need to be evaluated via Monte-Carlo-based numerical integration. For the state-of-the-art minimax exponential tilting (MET) method, we show that the complexity of each of its components can be greatly reduced through an integrand parameterization that utilizes the sparse inverse Cholesky factor produced by the Vecchia approximation, whose approximation error is often negligible relative to the Monte-Carlo error. Based on this idea, we derive algorithms that can estimate MVN probabilities and sample from truncated MVN distributions in linear time (and that are easily parallelizable) at the same convergence or acceptance rate as MET, whose complexity is cubic in the dimension of the MVN probability. We showcase the advantages of our methods relative to existing approaches using several simulated examples. We also analyze a groundwater-contamination dataset with over twenty thousand censored measurements to demonstrate the scalability of our method for partially censored Gaussian-process models.

A digital twin (DT) is a virtual representation of physical process, products and/or systems that requires a high-fidelity computational model for continuous update through the integration of sensor data and user input. In the context of laser powder bed fusion (LPBF) additive manufacturing, a digital twin of the manufacturing process can offer predictions for the produced parts, diagnostics for manufacturing defects, as well as control capabilities. This paper introduces a parameterized physics-based digital twin (PPB-DT) for the statistical predictions of LPBF metal additive manufacturing process. We accomplish this by creating a high-fidelity computational model that accurately represents the melt pool phenomena and subsequently calibrating and validating it through controlled experiments. In PPB-DT, a mechanistic reduced-order method-driven stochastic calibration process is introduced, which enables the statistical predictions of the melt pool geometries and the identification of defects such as lack-of-fusion porosity and surface roughness, specifically for diagnostic applications. Leveraging data derived from this physics-based model and experiments, we have trained a machine learning-based digital twin (PPB-ML-DT) model for predicting, monitoring, and controlling melt pool geometries. These proposed digital twin models can be employed for predictions, control, optimization, and quality assurance within the LPBF process, ultimately expediting product development and certification in LPBF-based metal additive manufacturing., Comment: arXiv admin note: text overlap with arXiv:2208.02907

Optical clock network requires the establishment of optical frequency transmission link between multiple optical clocks, utilizing narrow linewidth lasers. Despite achieving link noise levels of 10${^{-20}}$, the final accuracy is limited by the phase noise of the clock laser. Correlation spectroscopy is developed to transmit frequency information between two optical clocks directly, enabling optical clock comparison beyond the phase noise limit of clock lasers, and significantly enhancing the measurement accuracy or shorten the measurement time. In this letter, two compact transportable ${^{40}}$Ca${^+}$ clocks are employed to accomplish the correlation spectroscopy comparison, demonstrating an 10 cm level measurement accuracy of chronometric leveling using a mediocre clock laser with linewidth of 200 Hz. The relative frequency instability reaches $6.0\times10{^{-15}}/\sqrt{\tau/s}$, which is about 20 times better than the result with Rabi spectroscopy using the same clock laser. This research greatly reduces the harsh requirements on the performance of the clock laser, so that an ordinary stable-laser can also be employed in the construction of optical clock network, which is essential for the field applications, especially for the chronometric leveling.

Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. However, from the perspective of feature extraction, most existing pFL methods only focus on extracting global or personalized feature information during local training, which fails to meet the collaborative learning and personalization goals of pFL. To address this, we propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. We conduct extensive experiments on six datasets in three statistically heterogeneous settings and show the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy. Besides, GPFL mitigates overfitting and outperforms the baselines by up to 8.99% in accuracy., Comment: Accepted by ICCV2023

The event streams generated by dynamic vision sensors (DVS) are sparse and non-uniform in the spatial domain, while still dense and redundant in the temporal domain. Although spiking neural network (SNN), the event-driven neuromorphic model, has the potential to extract spatio-temporal features from the event streams, it is not effective and efficient. Based on the above, we propose an events sparsification spiking framework dubbed as Razor SNN, pruning pointless event frames progressively. Concretely, we extend the dynamic mechanism based on the global temporal embeddings, reconstruct the features, and emphasize the events effect adaptively at the training stage. During the inference stage, eliminate fruitless frames hierarchically according to a binary mask generated by the trained temporal embeddings. Comprehensive experiments demonstrate that our Razor SNN achieves competitive performance consistently on four events-based benchmarks: DVS 128 Gesture, N-Caltech 101, CIFAR10-DVS and SHD., Comment: Accepted by ICANN 2023 (Oral)

Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again. However, it is not economical to train diverse teacher models for the disposable distillation. In this paper, we introduce a new concept dubbed Avatars for distillation, which are the inference ensemble models derived from the teacher. Concretely, (1) For each iteration of distillation training, various Avatars are generated by a perturbation transformation. We validate that Avatars own higher upper limit of working capacity and teaching ability, aiding the student model in learning diverse and receptive knowledge perspectives from the teacher model. (2) During the distillation, we propose an uncertainty-aware factor from the variance of statistical differences between the vanilla teacher and Avatars, to adjust Avatars' contribution on knowledge transfer adaptively. Avatar Knowledge Distillation AKD is fundamentally different from existing methods and refines with the innovative view of unequal training. Comprehensive experiments demonstrate the effectiveness of our Avatars mechanism, which polishes up the state-of-the-art distillation methods for dense prediction without more extra computational cost. The AKD brings at most 0.7 AP gains on COCO 2017 for Object Detection and 1.83 mIoU gains on Cityscapes for Semantic Segmentation, respectively. Code is available at https://github.com/Gumpest/AvatarKD., Comment: Accepted by ACM MM 2023

Soft-thresholding has been widely used in neural networks. Its basic network structure is a two-layer convolution neural network with soft-thresholding. Due to the network's nature of nonlinearity and nonconvexity, the training process heavily depends on an appropriate initialization of network parameters, resulting in the difficulty of obtaining a globally optimal solution. To address this issue, a convex dual network is designed here. We theoretically analyze the network convexity and numerically confirm that the strong duality holds. This conclusion is further verified in the linear fitting and denoising experiments. This work provides a new way to convexify soft-thresholding neural networks., Comment: 13 pages,10 figures

Multi-task learning (MTL) aims at solving multiple related tasks simultaneously and has experienced rapid growth in recent years. However, MTL models often suffer from performance degeneration with negative transfer due to learning several tasks simultaneously. Some related work attributed the source of the problem is the conflicting gradients. In this case, it is needed to select useful gradient updates for all tasks carefully. To this end, we propose a novel optimization approach for MTL, named GDOD, which manipulates gradients of each task using an orthogonal basis decomposed from the span of all task gradients. GDOD decomposes gradients into task-shared and task-conflict components explicitly and adopts a general update rule for avoiding interference across all task gradients. This allows guiding the update directions depending on the task-shared components. Moreover, we prove the convergence of GDOD theoretically under both convex and non-convex assumptions. Experiment results on several multi-task datasets not only demonstrate the significant improvement of GDOD performed to existing MTL models but also prove that our algorithm outperforms state-of-the-art optimization methods in terms of AUC and Logloss metrics.

To achieve scalable and accurate inference for latent Gaussian processes, we propose a variational approximation based on a family of Gaussian distributions whose covariance matrices have sparse inverse Cholesky (SIC) factors. We combine this variational approximation of the posterior with a similar and efficient SIC-restricted Kullback-Leibler-optimal approximation of the prior. We then focus on a particular SIC ordering and nearest-neighbor-based sparsity pattern resulting in highly accurate prior and posterior approximations. For this setting, our variational approximation can be computed via stochastic gradient descent in polylogarithmic time per iteration. We provide numerical comparisons showing that the proposed double-Kullback-Leibler-optimal Gaussian-process approximation (DKLGP) can sometimes be vastly more accurate for stationary kernels than alternative approaches such as inducing-point and mean-field approximations at similar computational complexity., Comment: Accepted at the 2023 International Conference on Machine Learning (ICML). 18 pages with references and appendices, 14 figures

A visual single-object tracker is an indispensable component of underwater vehicles (UVs) in marine organism grasping tasks. Its accuracy and stability are imperative to guide the UVs to perform grasping behavior. Although single-object trackers show competitive performance in the challenge of underwater image degradation, there are still issues with sample imbalance and exclusion of similar objects that need to be addressed for application in marine organism grasping. This paper proposes Underwater OSTrack (UOSTrack), which consists of underwater image and open-air sequence hybrid training (UOHT), and motion-based post-processing (MBPP). The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions. The MBPP paradigm is proposed to exclude similar objects. It uses the estimation box predicted with a Kalman filter and the candidate boxes in the response map to relocate the lost tracked object in the candidate area. UOSTrack achieves an average performance improvement of 4.41% and 7.98% maximum compared to state-of-the-art methods on various benchmarks, respectively. Field experiments have verified the accuracy and stability of our proposed UOSTrack for UVs in marine organism grasping tasks. More details can be found at https://github.com/LiYunfengLYF/UOSTrack.

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in DMF. We prove that, for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning., Comment: 15 pages, 8 figures

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: \url{https://github.com/tencent-ailab/RLogist}., Comment: accepted by AAAI 2023

This paper introduces JAX-FEM, an open-source differentiable finite element method (FEM) library. Constructed on top of Google JAX, a rising machine learning library focusing on high-performance numerical computing, JAX-FEM is implemented with pure Python while scalable to efficiently solve problems with moderate to large sizes. For example, in a 3D tensile loading problem with 7.7 million degrees of freedom, JAX-FEM with GPU achieves around 10$\times$ acceleration compared to a commercial FEM code depending on platform. Beyond efficiently solving forward problems, JAX-FEM employs the automatic differentiation technique so that inverse problems are solved in a fully automatic manner without the need to manually derive sensitivities. Examples of 3D topology optimization of nonlinear materials are shown to achieve optimal compliance. Finally, JAX-FEM is an integrated platform for machine learning-aided computational mechanics. We show an example of data-driven multi-scale computations of a composite material where JAX-FEM provides an all-in-one solution from microscopic data generation and model training to macroscopic FE computations. The source code of the library and these examples are shared with the community to facilitate computational mechanics research.

Undersampling can accelerate the signal acquisition but at the cost of bringing in artifacts. Removing these artifacts is a fundamental problem in signal processing and this task is also called signal reconstruction. Through modeling signals as the superimposed exponential functions, deep learning has achieved fast and high-fidelity signal reconstruction by training a mapping from the undersampled exponentials to the fully sampled ones. However, the mismatch, such as the sampling rate of undersampling, the organ and the contrast of imaging, between the training and target data will heavily compromise the reconstruction. To address this issue, we propose Alternating Deep Low-Rank (ADLR), which combines deep learning solvers and classic optimization solvers. Experiments on the reconstruction of synthetic and realistic biomedical magnetic resonance signals demonstrate that ADLR can effectively mitigate the mismatch issue and achieve lower reconstruction errors than state-of-the-art methods., Comment: 12 pages

Rapid developments in satellite remote-sensing technology have enabled the collection of geospatial data on a global scale, hence increasing the need for covariance functions that can capture spatial dependence on spherical domains. We propose a general method of constructing nonstationary, locally anisotropic covariance functions on the sphere based on covariance functions in R^3. We also provide theorems that specify the conditions under which the resulting correlation function is isotropic or axially symmetric. For large datasets on the sphere commonly seen in modern applications, the Vecchia approximation is used to achieve higher scalability on statistical inference. The importance of flexible covariance structures is demonstrated numerically using simulated data and a precipitation dataset.

Understanding the thermal behavior of additive manufacturing (AM) processes is crucial for enhancing the quality control and enabling customized process design. Most purely physics-based computational models suffer from intensive computational costs and the need of calibrating unknown parameters, thus not suitable for online control and iterative design application. Data-driven models taking advantage of the latest developed computational tools can serve as a more efficient surrogate, but they are usually trained over a large amount of simulation data and often fail to effectively use small but high-quality experimental data. In this work, we developed a hybrid physics-based data-driven thermal modeling approach of AM processes using physics-informed neural networks. Specifically, partially observed temperature data measured from an infrared camera is combined with the physics laws to predict full-field temperature history and to discover unknown material and process parameters. In the numerical and experimental examples, the effectiveness of adding auxiliary training data and using the pretrained model on training efficiency and prediction accuracy, as well as the ability to identify unknown parameters with partially observed data, are demonstrated. The results show that the hybrid thermal model can effectively identify unknown parameters and capture the full-field temperature accurately, and thus it has the potential to be used in iterative process design and real-time process control of AM.

Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However, not every pixel contributes equally to the performance, and a good student should learn from what really matters to the teacher. In this paper, we introduce a learnable embedding dubbed receptive token to localize those pixels of interests (PoIs) in the feature map, with a distillation mask generated via pixel-wise attention. Then the distillation will be performed on the mask via pixel-wise reconstruction. In this way, a distillation mask actually indicates a pattern of pixel dependencies within feature maps of teacher. We thus adopt multiple receptive tokens to investigate more sophisticated and informative pixel dependencies to further enhance the distillation. To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks. Our method dubbed MasKD is simple and practical, and needs no priors of tasks in application. Experiments show that our MasKD can achieve state-of-the-art performance consistently on object detection and semantic segmentation benchmarks. Code is available at: https://github.com/hunto/MasKD ., Comment: ICLR 2023

We introduce a Power-of-Two low-bit post-training quantization(PTQ) method for deep neural network that meets hardware requirements and does not call for long-time retraining. Power-of-Two quantization can convert the multiplication introduced by quantization and dequantization to bit-shift that is adopted by many efficient accelerators. However, the Power-of-Two scale factors have fewer candidate values, which leads to more rounding or clipping errors. We propose a novel Power-of-Two PTQ framework, dubbed RAPQ, which dynamically adjusts the Power-of-Two scales of the whole network instead of statically determining them layer by layer. It can theoretically trade off the rounding error and clipping error of the whole network. Meanwhile, the reconstruction method in RAPQ is based on the BN information of every unit. Extensive experiments on ImageNet prove the excellent performance of our proposed method. Without bells and whistles, RAPQ can reach accuracy of 65% and 48% on ResNet-18 and MobileNetV2 respectively with weight INT2 activation INT4. We are the first to propose the more constrained but hardware-friendly Power-of-Two quantization scheme for low-bit PTQ specially and prove that it can achieve nearly the same accuracy as SOTA PTQ method. The code was released., Comment: This paper was accepted by IJCAI 2022. Pytorch implementation of RAPQ: https://github.com/BillAmihom/RAPQ

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining parameters in pruned networks inevitably bring a great challenge to fine-tuning to restore accuracy. To address this challenge, we propose a novel method that first linearly over-parameterizes the compact layers in pruned networks to enlarge the number of fine-tuning parameters and then re-parameterizes them to the original layers after fine-tuning. Specifically, we equivalently expand the convolution/linear layer with several consecutive convolution/linear layers that do not alter the current output feature maps. Furthermore, we utilize similarity-preserving knowledge distillation that encourages the over-parameterized block to learn the immediate data-to-data similarities of the corresponding dense layer to maintain its feature learning ability. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet which significantly outperforms the vanilla fine-tuning strategy, especially for large pruning ratio.

To cater for the diverse experiment requirements at the High Energy Photon Source (HEPS) with often limited human resources, Bluesky is chosen as the basis for our software framework, Mamba. In our attempt to address Bluesky's lack of integrated GUIs, command injection with feedback is chosen as the main way for the GUIs to cooperate with the CLI; a RPC service is provided, which also covers functionalities unsuitable for command injection, as well as pushing of status updates. In order to fully support high-frequency applications like fly scans, Bluesky's support for asynchronous control is being improved; to support high-throughput experiments, Mamba Data Worker (MDW) is being developed to cover the complexity in asynchronous online data processing for these experiments. To systematically simplify the specification of metadata, scan parameters and data-processing graphs for each type of experiments, an experiment parameter generator (EPG) will be developed; experiment-specific modules to automate preparation steps will also be made. The integration of off-the-shelf code in Mamba for domain-specific needs is under investigation, and Mamba GUI Studio (MGS) is being developed to simplify the implementation and integration of GUIs., Comment: 9 pages, 6 figures, accepted for J. Synchrotron Rad

Gaussian process (GP) regression is a flexible, nonparametric approach to regression that naturally quantifies uncertainty. In many applications, the number of responses and covariates are both large, and a goal is to select covariates that are related to the response. For this setting, we propose a novel, scalable algorithm, coined VGPR, which optimizes a penalized GP log-likelihood based on the Vecchia GP approximation, an ordered conditional approximation from spatial statistics that implies a sparse Cholesky factor of the precision matrix. We traverse the regularization path from strong to weak penalization, sequentially adding candidate covariates based on the gradient of the log-likelihood and deselecting irrelevant covariates via a new quadratic constrained coordinate descent algorithm. We propose Vecchia-based mini-batch subsampling, which provides unbiased gradient estimators. The resulting procedure is scalable to millions of responses and thousands of covariates. Theoretical analysis and numerical studies demonstrate the improved scalability and accuracy relative to existing methods., Comment: 30 pages, 9 figures

In this paper, we use the generalized q-polynomials with double q-binomial coefficients and homogeneous q-operators [J. Difference Equ. Appl. 20 (2014), 837--851.] to construct q-difference equations with seven variables, which generalize recent works of Jia et al [Symmetry 2021, 13, 1222.]. In addition, we derive Rogers formulas, extended Rogers formulas and Srivastava--Agarwal type bilinear generating functions for generalized q-polynomials, which generalize generating functions for Cigler's polynomials [J. Difference Equ. Appl. 24 (2018), 479--502.]. Finally, we also derive mixed generating functions using q-difference equations.

Current multi-physics Finite Element Method (FEM) solvers are complex systems in terms of both their mathematical complexity and lines of code. This paper proposes a skeleton generic FEM solver, named MetaFEM, in total about 5,000 lines of Julia code, which translates generic input Partial Differential Equation (PDE) weak forms into corresponding GPU-accelerated simulations with a grammar similar to FEniCS or FreeFEM. Two novel approaches differentiate MetaFEM from the common solvers: (1) the FEM kernel is based on an original theory/algorithm which explicitly processes meta-expressions, as the name suggests, and (2) the symbolic engine is a rule-based Computer Algebra System (CAS), i.e., the equations are rewritten/derived according to a set of rewriting rules instead of going through completely fixed routines, supporting easy customization by developers. Example cases in thermal conduction, linear elasticity and incompressible flow are presented to demonstrate utility.

The extreme and repeated temperature variation during additive manufacturing of metal parts has a large effect on the resulting material microstructure and properties. The ability to accurately predict this temperature field in detail, and relate it quantitatively to structure and properties, is a key step in predicting part performance and optimizing process design. In this work, a finite element simulation of the Directed Energy Deposition (DED) process is used to predict the space- and time-dependent temperature field during the multi-layer build process for Inconel 718 walls. The thermal model is validated using the dynamic infrared (IR) images captured in situ during the DED builds, showing good agreement with experimental measurements. The relationship between predicted cooling rate, microstructural features, and mechanical properties is examined, and cooling rate alone is found to be insufficient in giving quantitative property predictions. Because machine learning offers an efficient way to identify important features from series data, we apply a 1D convolutional neural network (CNN) data-driven framework to automatically extract the dominant predictive features from simulated temperature history. The relationship between the CNN-extracted features and the mechanical properties is studied. To interpret how CNN performs in intermediate layers, we visualize the extracted features produced on each convolutional layer by a trained CNN. Our results show that the results predicted by the CNN agree well with experimental measurements and give insights into physical mechanisms of microstructure evolution and mechanical properties.

Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless, with the fixed size of patches in ViT, the class token in deep layer focuses on the global receptive field and cannot generate multi-granularity features for FGVR. To capture region attention without box annotations and compensate for ViT shortcomings in FGVR, we propose a novel method named Adaptive attention multi-scale Fusion Transformer (AFTrans). The Selective Attention Collection Module (SACM) in our approach leverages attention weights in ViT and filters them adaptively to correspond with the relative importance of input patches. The multiple scales (global and local) pipeline is supervised by our weights sharing encoder and can be easily trained end-to-end. Comprehensive experiments demonstrate that AFTrans can achieve SOTA performance on three published fine-grained benchmarks: CUB-200-2011, Stanford Dogs and iNat2017.

Channel pruning is one of the major compression approaches for deep neural networks. While previous pruning methods have mostly focused on identifying unimportant channels, channel pruning is considered as a special case of neural architecture search in recent years. However, existing methods are either complicated or prone to sub-optimal pruning. In this paper, we propose a pruning framework that adaptively determines the number of each layer's channels as well as the wights inheritance criteria for sub-network. Firstly, evaluate the importance of each block in the network based on the mean of the scaling parameters of the BN layers. Secondly, use the bisection method to quickly find the compact sub-network satisfying the budget. Finally, adaptively and efficiently choose the weight inheritance criterion that fits the current architecture and fine-tune the pruned network to recover performance. AdaPruner allows to obtain pruned network quickly, accurately and efficiently, taking into account both the structure and initialization weights. We prune the currently popular CNN models (VGG, ResNet, MobileNetV2) on different image classification datasets, and the experimental results demonstrate the effectiveness of our proposed method. On ImageNet, we reduce 32.8% FLOPs of MobileNetV2 with only 0.62% decrease for top-1 accuracy, which exceeds all previous state-of-the-art channel pruning methods. The code will be released.

Spiking neural network (SNN), compared with depth neural network (DNN), has faster processing speed, lower energy consumption and more biological interpretability, which is expected to approach Strong AI. Reinforcement learning is similar to learning in biology. It is of great significance to study the combination of SNN and RL. We propose the reinforcement learning method of spike distillation network (SDN) with STBP. This method uses distillation to effectively avoid the weakness of STBP, which can achieve SOTA performance in classification, and can obtain a smaller, faster convergence and lower power consumption SNN reinforcement learning model. Experiments show that our method can converge faster than traditional SNN reinforcement learning and DNN reinforcement learning methods, about 1000 epochs faster, and obtain SNN 200 times smaller than DNN. We also deploy SDN to the PKU nc64c chip, which proves that SDN has lower power consumption than DNN, and the power consumption of SDN is more than 600 times lower than DNN on large-scale devices. SDN provides a new way of SNN reinforcement learning, and can achieve SOTA performance, which proves the possibility of further development of SNN reinforcement learning., Comment: 7 pages, 5 figures, conference

We present a novel computational paradigm for process design in manufacturing processes that incorporates simulation responses to optimize manufacturing process parameters in high-dimensional temporal and spatial design spaces. We developed a differentiable finite element analysis framework using automatic differentiation which allows accurate optimization of challenging process parameters such as time-series laser power. We demonstrate the capability of our proposed method through three illustrative case studies in additive manufacturing for: (i) material and process parameter inference using partial observable data, (ii) controlling time-series thermal behavior, and (iii) stabilizing melt pool depth. This research opens new avenues for high-dimensional manufacturing design using solid mechanics simulation tools such as finite element methods. Our codes are made publicly available for the research community at https://github.com/mojtabamozaffar/differentiable-simulation-am.

Understanding the atomic structure and structural instability of organic-inorganic hybrid perovskites is the key to appreciate their remarkable photoelectric properties and failure mechanism. Here, using low-dose imaging technique by direct-detection electron-counting camera in transmission electron microscope, we investigate the atomic structure and decomposition pathway of CH3NH3PbI3 (MAPbI3) at the atomic scale. We successfully image the atomic structure of perovskite in real space under ultra-low electron dose condition, and observe a two-step decomposition process, i.e. initial loss of MA followed by the collapse of perovskite structure into 6H-PbI2 with their critical threshold dose also determined. Interestingly, an intermediate phase (MA0.5PbI3) with locally ordered vacancies can robustly exist before perovskite collapses, enlightening strategies for prevention and recovery of perovskite structure during degradation. Associated with structure evolution, the bandgap gradually increases from ~1.6 eV to ~2.1 eV, and it is found that both C-N and N-H bonds can be destroyed under irradiation, releasing NH3 and leaving hydrocarbons. These findings enhance our understanding of the photoelectric properties and failure mechanism of MAPbI3, providing potential strategy into material optimization.

Concurrent analysis of composite materials can provide the interaction among scales for better composite design, analysis, and performance prediction. A data-driven concurrent n-scale modeling theory ($\textrm{FExSCA}^\textrm{n-1}$) is proposed in this paper utilizing a mechanistic reduced order model (ROM) called self-consistent clustering analysis (SCA). We demonstrated this theory with a $\textrm{FExSCA}^2$ approach to study the 3-scale woven carbon fiber reinforced polymer (CFRP) laminate structure. $\textrm{FExSCA}^2$ significantly reduced expensive 3D nested composite representative volume elements (RVEs) computation for woven and unidirectional (UD) composite structures by developing a material database. The modeling procedure is established by integrating the material database into a woven CFRP structural numerical model, formulating a concurrent 3-scale modeling framework. This framework provides an accurate prediction for the structural performance (e.g., nonlinear structural behavior under tensile load), as well as the woven and UD physics field evolution. The concurrent modeling results are validated against physical tests that link structural performance to the basic material microstructures. The proposed methodology provides a comprehensive predictive modeling procedure applicable to general composite materials aiming to reduce laborious experiments needed., Comment: 12 Figures

At present, most research on the fairness of recommender systems is conducted either from the perspective of customers or from the perspective of product (or service) providers. However, such a practice ignores the fact that when fairness is guaranteed to one side, the fairness and rights of the other side are likely to reduce. In this paper, we consider recommendation scenarios from the perspective of two sides (customers and providers). From the perspective of providers, we consider the fairness of the providers' exposure in recommender system. For customers, we consider the fairness of the reduced quality of recommendation results due to the introduction of fairness measures. We theoretically analyzed the relationship between recommendation quality, customers fairness, and provider fairness, and design a two-sided fairness-aware recommendation model (TFROM) for both customers and providers. Specifically, we design two versions of TFROM for offline and online recommendation. The effectiveness of the model is verified on three real-world data sets. The experimental results show that TFROM provides better two-sided fairness while still maintaining a higher level of personalization than the baseline algorithms., Comment: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

The reference frame memory accesses in inter prediction result in high DRAM bandwidth requirement and power consumption. This problem is more intensive by the adoption of intra block copy (IBC), a new coding tool in the screen content coding (SCC) extension to High Efficiency Video Coding (HEVC). In this paper, we propose a lossless recompression scheme that compresses the reference blocks in intra prediction, i.e., intra block copy, before storing them into DRAM to alleviate this problem. The proposal performs pixel-wise texture analysis with an edge-based adaptive prediction method yet no signaling for direction in bitstreams, thus achieves a high gain for compression. Experimental results demonstrate that the proposed scheme shows a 72% data reduction rate on average, which solves the memory bandwidth problem., Comment: ISCAS 2021 accepted as oral

Tracking and collecting fast-evolving online discussions provides vast data for studying social media usage and its role in people's public lives. However, collecting social media data using a static set of keywords fails to satisfy the growing need to monitor dynamic conversations and to study fast-changing topics. We propose a dynamic keyword search method to maximize the coverage of relevant information in fast-evolving online discussions. The method uses word embedding models to represent the semantic relations between keywords and predictive models to forecast the future time series. We also implement a visual user interface to aid in the decision-making process in each round of keyword updates. This allows for both human-assisted tracking and fully-automated data collection. In simulations using historical #MeToo data in 2017, our human-assisted tracking method outperforms the traditional static baseline method significantly, with 37.1% higher F-1 score than traditional static monitors in tracking the top trending keywords. We conduct a contemporary case study to cover dynamic conversations about the recent Presidential Inauguration and to test the dynamic data collection system. Our case studies reflect the effectiveness of our process and also points to the potential challenges in future deployment., Comment: Preprint, Under Review