Search

In this work, we introduce the Federated Quantum-Train (QT) framework, which integrates the QT model into federated learning to leverage quantum computing for distributed learning systems. Quantum client nodes employ Quantum Neural Networks (QNNs) and a mapping model to generate local target model parameters, which are updated and aggregated at a central node. Testing with a VGG-like convolutional neural network on the CIFAR-10 dataset, our approach significantly reduces qubit usage from 19 to as low as 8 qubits while reducing generalization error. The QT method mitigates overfitting observed in classical models, aligning training and testing accuracy and improving performance in highly compressed models. Notably, the Federated QT framework does not require a quantum computer during inference, enhancing practicality given current quantum hardware limitations. This work highlights the potential of integrating quantum techniques into federated learning, paving the way for advancements in quantum machine learning and distributed learning systems., Comment: 6 pages, 5 figures

We investigate numerically the identification of relevant structural features that contribute to the dynamical heterogeneity in a model glass-forming liquid. By employing the recently proposed information imbalance technique, we select these features from a range of physically motivated descriptors. This selection process is performed in a supervised manner (using both dynamical and structural data) and an unsupervised manner (using only structural data). We then apply the selected features to predict future dynamics using a machine learning technique. Finally, we discuss the potential applications of this approach in identifying the dominant mechanisms governing the glassy slow dynamics.

Gesture recognition based on surface electromyography (sEMG) has achieved significant progress in human-machine interaction (HMI). However, accurately recognizing predefined gestures within a closed set is still inadequate in practice; a robust open-set system needs to effectively reject unknown gestures while correctly classifying known ones. To handle this challenge, we first report prediction inconsistency discovered for unknown classes due to ensemble diversity, which can significantly facilitate the detection of unknown classes. Based on this insight, we propose an ensemble learning approach, PredIN, to explicitly magnify the prediction inconsistency by enhancing ensemble diversity. Specifically, PredIN maximizes the class feature distribution inconsistency among ensemble members to enhance diversity. Meanwhile, it optimizes inter-class separability within an individual ensemble member to maintain individual performance. Comprehensive experiments on various benchmark datasets demonstrate that the PredIN outperforms state-of-the-art methods by a clear margin.Our proposed method simultaneously achieves accurate closed-set classification for predefined gestures and effective rejection for unknown gestures, exhibiting its efficacy and superiority in open-set gesture recognition based on sEMG., Comment: Under review

This paper introduces a noise-aware distributed Quantum Approximate Optimization Algorithm (QAOA) tailored for execution on near-term quantum hardware. Leveraging a distributed framework, we address the limitations of current Noisy Intermediate-Scale Quantum (NISQ) devices, which are hindered by limited qubit counts and high error rates. Our approach decomposes large QAOA problems into smaller subproblems, distributing them across multiple Quantum Processing Units (QPUs) to enhance scalability and performance. The noise-aware strategy incorporates error mitigation techniques to optimize qubit fidelity and gate operations, ensuring reliable quantum computations. We evaluate the efficacy of our framework using the HamilToniQ Benchmarking Toolkit, which quantifies the performance across various quantum hardware configurations. The results demonstrate that our distributed QAOA framework achieves significant improvements in computational speed and accuracy, showcasing its potential to solve complex optimization problems efficiently in the NISQ era. This work sets the stage for advanced algorithmic strategies and practical quantum system enhancements, contributing to the broader goal of achieving quantum advantage.

Affective Behavior Analysis aims to develop emotionally intelligent technology that can recognize and respond to human emotions. To advance this, the 7th Affective Behavior Analysis in-the-wild (ABAW) competition establishes two tracks: i.e., the Multi-task Learning (MTL) Challenge and the Compound Expression (CE) challenge based on Aff-Wild2 and C-EXPR-DB datasets. In this paper, we present our methods and experimental results for the two competition tracks. Specifically, it can be summarized in the following four aspects: 1) To attain high-quality facial features, we train a Masked-Auto Encoder in a self-supervised manner. 2) We devise a temporal convergence module to capture the temporal information between video frames and explore the impact of window size and sequence length on each sub-task. 3) To facilitate the joint optimization of various sub-tasks, we explore the impact of sub-task joint training and feature fusion from individual tasks on each task performance improvement. 4) We utilize curriculum learning to transition the model from recognizing single expressions to recognizing compound expressions, thereby improving the accuracy of compound expression recognition. Extensive experiments demonstrate the superiority of our designs., Comment: Techical Report for 7th ABAW Competition

We present novel path-slicing strategies integrated with quantum local search to optimize solutions for the Traveling Salesman Problem (TSP), addressing the limitations of current Noisy Intermediate-Scale Quantum (NISQ) technologies. Our hybrid quantum-classical approach leverages classical path initialization and quantum optimization to effectively manage the computational challenges posed by the TSP. We explore various path slicing methods, including k-means and anti-k-means clustering, to divide the TSP into manageable subproblems. These are then solved using quantum or classical solvers. Our analysis, performed on multiple TSP instances from the TSPlib, demonstrates the ability of our strategies to achieve near-optimal solutions efficiently, highlighting significant improvements in solving efficiency and resource utilization. This approach paves the way for future applications in larger combinatorial optimization scenarios, advancing the field of quantum optimization., Comment: 5 pages, 4 figures

Existing Masked Image Modeling (MIM) depends on a spatial patch-based masking-reconstruction strategy to perceive objects'features from unlabeled images, which may face two limitations when applied to chest CT: 1) inefficient feature learning due to complex anatomical details presented in CT images, and 2) suboptimal knowledge transfer owing to input disparity between upstream and downstream models. To address these issues, we propose a new MIM method named Tissue-Contrastive Semi-Masked Autoencoder (TCS-MAE) for modeling chest CT images. Our method has two novel designs: 1) a tissue-based masking-reconstruction strategy to capture more fine-grained anatomical features, and 2) a dual-AE architecture with contrastive learning between the masked and original image views to bridge the gap of the upstream and downstream models. To validate our method, we systematically investigate representative contrastive, generative, and hybrid self-supervised learning methods on top of tasks involving segmenting pneumonia, mediastinal tumors, and various organs. The results demonstrate that, compared to existing methods, our TCS-MAE more effectively learns tissue-aware representations, thereby significantly enhancing segmentation performance across all tasks.

We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with either enhanced fidelity or increased diversity. Our approach involves manipulating the distribution of training and generated data through a novel metric for individual samples, named pseudo density, which is based on the nearest-neighbor information from real samples. Our approach offers three distinct techniques to adjust the fidelity and diversity of deep generative models: 1) Per-sample perturbation, enabling precise adjustments for individual samples towards either more common or more unique characteristics; 2) Importance sampling during model inference to enhance either fidelity or diversity in the generated data; 3) Fine-tuning with importance sampling, which guides the generative model to learn an adjusted distribution, thus controlling fidelity and diversity. Furthermore, our fine-tuning method demonstrates the ability to improve the Frechet Inception Distance (FID) for pre-trained generative models with minimal iterations.

Flood prediction is a critical challenge in the context of climate change, with significant implications for ecosystem preservation, human safety, and infrastructure protection. In this study, we tackle this problem by applying the Quantum-Train (QT) technique to a forecasting Long Short-Term Memory (LSTM) model trained by Quantum Machine Learning (QML) with significant parameter reduction. The QT technique, originally successful in the A Matter of Taste challenge at QHack 2024, leverages QML to reduce the number of trainable parameters to a polylogarithmic function of the number of parameters in a classical neural network (NN). This innovative framework maps classical NN weights to a Hilbert space, altering quantum state probability distributions to adjust NN parameters. Our approach directly processes classical data without the need for quantum embedding and operates independently of quantum computing resources post-training, making it highly practical and accessible for real-world flood prediction applications. This model aims to improve the efficiency of flood forecasts, ultimately contributing to better disaster preparedness and response., Comment: 6 pages, 4 figures

We present a novel approach called differentially private stochastic block coordinate descent (DP-SBCD) for training neural networks with provable guarantees of differential privacy under the hidden state assumption. Our methodology incorporates Lipschitz neural networks and decomposes the training process of the neural network into sub-problems, each corresponding to the training of a specific layer. By doing so, we extend the analysis of differential privacy under the hidden state assumption to encompass non-convex problems and algorithms employing proximal gradient descent. Furthermore, in contrast to existing methods, we adopt a novel approach by utilizing calibrated noise sampled from adaptive distributions, yielding improved empirical trade-offs between utility and privacy.

Quantum reinforcement learning utilizes quantum layers to process information within a machine learning model. However, both pure and hybrid quantum reinforcement learning face challenges such as data encoding and the use of quantum computers during the inference stage. We apply the Quantum-Train method to reinforcement learning tasks, called QTRL, training the classical policy network model using a quantum machine learning model with polylogarithmic parameter reduction. This QTRL approach eliminates the data encoding issues of conventional quantum machine learning and reduces the training parameters of the corresponding classical policy network. Most importantly, the training result of the QTRL is a classical model, meaning the inference stage only requires classical computer. This is extremely practical and cost-efficient for reinforcement learning tasks, where low-latency feedback from the policy model is essential., Comment: 6 pages, 1 figure

Motor imagery electroencephalograph (MI-EEG) decoding plays a crucial role in developing motor imagery brain-computer interfaces (MI-BCIs). However, decoding intentions from MI remains challenging due to the inherent complexity of EEG signals relative to the small-sample size. In this paper, we propose an Efficient Dual Prototype Network (EDPNet) to enable accurate and fast MI decoding. EDPNet employs a lightweight adaptive spatial-spectral fusion module, which promotes more efficient information fusion between multiple EEG electrodes. Subsequently, a parameter-free multi-scale variance pooling module extracts more comprehensive temporal features. Furthermore, we introduce dual prototypical learning to optimize the feature space distribution and training process, thereby improving the model's generalization ability on small-sample MI datasets. Our experimental results show that the EDPNet outperforms state-of-the-art models with superior classification accuracy and kappa values (84.11% and 0.7881 for dataset BCI competition IV 2a, 86.65% and 0.7330 for dataset BCI competition IV 2b). Additionally, we use the BCI competition III IVa dataset with fewer training data to further validate the generalization ability of the proposed EDPNet. We also achieve superior performance with 82.03% classification accuracy. Benefiting from the lightweight parameters and superior decoding accuracy, our EDPNet shows great potential for MI-BCI applications. The code is publicly available at https://github.com/hancan16/EDPNet.

We present UniPlane, a novel method that unifies plane detection and reconstruction from posed monocular videos. Unlike existing methods that detect planes from local observations and associate them across the video for the final reconstruction, UniPlane unifies both the detection and the reconstruction tasks in a single network, which allows us to directly optimize final reconstruction quality and fully leverage temporal information. Specifically, we build a Transformers-based deep neural network that jointly constructs a 3D feature volume for the environment and estimates a set of per-plane embeddings as queries. UniPlane directly reconstructs the 3D planes by taking dot products between voxel embeddings and the plane embeddings followed by binary thresholding. Extensive experiments on real-world datasets demonstrate that UniPlane outperforms state-of-the-art methods in both plane detection and reconstruction tasks, achieving +4.6 in F-score in geometry as well as consistent improvements in other geometry and segmentation metrics., Comment: arXiv admin note: substantial text overlap with arXiv:2206.07710 by other authors

The forecasting of disease progression from images is a holy grail for clinical decision making. However, this task is complicated by the inherent high dimensionality, temporal sparsity and sampling irregularity in longitudinal image acquisitions. Existing methods often rely on extracting hand-crafted features and performing time-series analysis in this vector space, leading to a loss of rich spatial information within the images. To overcome these challenges, we introduce ImageFlowNet, a novel framework that learns latent-space flow fields that evolve multiscale representations in joint embedding spaces using neural ODEs and SDEs to model disease progression in the image domain. Notably, ImageFlowNet learns multiscale joint representation spaces by combining cohorts of patients together so that information can be transferred between the patient samples. The dynamics then provide plausible trajectories of progression, with the SDE providing alternative trajectories from the same starting point. We provide theoretical insights that support our formulation of ODEs, and motivate our regularizations involving high-level visual features, latent space organization, and trajectory smoothness. We then demonstrate ImageFlowNet's effectiveness through empirical evaluations on three longitudinal medical image datasets depicting progression in retinal geographic atrophy, multiple sclerosis, and glioblastoma., Comment: Fixed some typos. Merged multibib

As a fundamental structural feature, the symmetry of materials determines the exotic quantum properties in transition metal dichalcogenides (TMDs) with charge density wave (CDW). Breaking the inversion symmetry, the Janus structure, an artificially constructed lattice, provides an opportunity to tune the CDW states and the related properties. However, limited by the difficulties in atomic-level fabrication and material stability, the experimental visualization of the CDW states in 2D TMDs with Janus structure is still rare. Here, using surface selenization of VTe2, we fabricated monolayer Janus VTeSe. With scanning tunneling microscopy, an unusual root13-root13 CDW state with threefold rotational symmetry breaking was observed and characterized. Combined with theoretical calculations, we find this CDW state can be attributed to the charge modulation in the Janus VTeSe, beyond the conventional electron-phonon coupling. Our findings provide a promising platform for studying the CDW states and artificially tuning the electronic properties toward the applications.

Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore the nature of prompt generalization on unknown domains, we conduct pilot experiments and find that (i) Prompts gaining more attention weight from PLMs' deep layers are more generalizable and (ii) Prompts with more stable attention distributions in PLMs' deep layers are more generalizable. Thus, we offer a fresh objective towards domain-generalizable prompts optimization named "Concentration", which represents the "lookback" attention from the current decoding token to the prompt tokens, to increase the attention strength on prompts and reduce the fluctuation of attention distribution. We adapt this new objective to popular soft prompt and hard prompt optimization methods, respectively. Extensive experiments demonstrate that our idea improves comparison prompt optimization methods by 1.42% for soft prompt generalization and 2.16% for hard prompt generalization in accuracy on the multi-source domain generalization setting, while maintaining satisfying in-domain performance. The promising results validate the effectiveness of our proposed prompt optimization objective and provide key insights into domain-generalizable prompts., Comment: Submitted to NeurIPS 2024, Preprint, Under review

The past two decades have yielded several new measurements and reanalysis of older measurements of the neutron lifetime. These have led to a 4.4 standard deviation discrepancy between the most precise measurements of the neutron decay rate producing protons in cold neutron beams and the most precise lifetime measured in neutron storage experiments. Here we publish an analysis of the recently published UCN aimed a searching for an explanation of this difference using the model proposed by Koch and Hummel.

We propose an innovative Parallel Quantum Local Search (PQLS) methodology that leverages the capabilities of small-scale quantum computers to efficiently address complex combinatorial optimization problems. Traditional Quantum Local Search (QLS) methods face limitations due to the sequential nature of solving sub-problems, which arises from dependencies between their solutions. Our approach transcends this constraint by simultaneously executing multiple QLS pathways and aggregating their most effective outcomes at certain intervals to establish a ``generation''. Each subsequent generation commences with the optimal solution from its predecessor, thereby significantly accelerating the convergence towards an optimal solution. Our findings demonstrate the profound impact of parallel quantum computing in enhancing the resolution of Ising problems, which are synonymous with combinatorial optimization challenges., Comment: 4 pages, 2 figures

The surge of interest in culturally aware and adapted Natural Language Processing (NLP) has inspired much recent research. However, the lack of common understanding of the concept of "culture" has made it difficult to evaluate progress in this emerging area. Drawing on prior research in NLP and related fields, we propose an extensive taxonomy of elements of culture that can provide a systematic framework for analyzing and understanding research progress. Using the taxonomy, we survey existing resources and models for culturally aware and adapted NLP, providing an overview of the state of the art and the research gaps that still need to be filled.

Deriving co-speech 3D gestures has seen tremendous progress in virtual avatar animation. Yet, the existing methods often produce stiff and unreasonable gestures with unseen human speech inputs due to the limited 3D speech-gesture data. In this paper, we propose CoCoGesture, a novel framework enabling vivid and diverse gesture synthesis from unseen human speech prompts. Our key insight is built upon the custom-designed pretrain-fintune training paradigm. At the pretraining stage, we aim to formulate a large generalizable gesture diffusion model by learning the abundant postures manifold. Therefore, to alleviate the scarcity of 3D data, we first construct a large-scale co-speech 3D gesture dataset containing more than 40M meshed posture instances across 4.3K speakers, dubbed GES-X. Then, we scale up the large unconditional diffusion model to 1B parameters and pre-train it to be our gesture experts. At the finetune stage, we present the audio ControlNet that incorporates the human voice as condition prompts to guide the gesture generation. Here, we construct the audio ControlNet through a trainable copy of our pre-trained diffusion model. Moreover, we design a novel Mixture-of-Gesture-Experts (MoGE) block to adaptively fuse the audio embedding from the human speech and the gesture features from the pre-trained gesture experts with a routing mechanism. Such an effective manner ensures audio embedding is temporal coordinated with motion features while preserving the vivid and diverse gesture generation. Extensive experiments demonstrate that our proposed CoCoGesture outperforms the state-of-the-art methods on the zero-shot speech-to-gesture generation. The dataset will be publicly available at: https://mattie-e.github.io/GES-X/, Comment: The dataset will be released as soon as possible

Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query sample. The fundamental problem in VICL is how to select the best prompt to activate its power as much as possible, which is equivalent to the ranking problem to test the in-context behavior of each candidate in the alternative set and select the best one. To utilize more appropriate ranking metric and leverage more comprehensive information among the alternative set, we propose a novel in-context example selection framework to approximately identify the global optimal prompt, i.e. choosing the best performing in-context examples from all alternatives for each query sample. Our method, dubbed Partial2Global, adopts a transformer-based list-wise ranker to provide a more comprehensive comparison within several alternatives, and a consistency-aware ranking aggregator to generate globally consistent ranking. The effectiveness of Partial2Global is validated through experiments on foreground segmentation, single object detection and image colorization, demonstrating that Partial2Global selects consistently better in-context examples compared with other methods, and thus establish the new state-of-the-arts.

The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex problem. The sampling for diffusion models is done by solving either the probability flow ODE or diffusion SDE wherein a neural network approximates the score function or related quantity, allowing a numerical ODE/SDE solver to be used. However, na\"ive backpropagation techniques are memory intensive, requiring the storage of all intermediate states, and face additional complexity in handling the injected noise from the diffusion term of the diffusion SDE. We propose a novel method based on the stochastic adjoint sensitivity method to calculate the gradientwith respect to the initial noise, conditional information, and model parameters by solving an additional SDE whose solution is the gradient of the diffusion SDE. We exploit the unique construction of diffusion SDEs to further simplify the formulation of the adjoint diffusion SDE and use a change-of-variables to simplify the solution to an exponentially weighted integral. Using this formulation we derive a custom solver for the adjoint SDE as well as the simpler adjoint ODE. The proposed adjoint diffusion solvers can efficiently compute the gradients for both the probability flow ODE and diffusion SDE for latents and parameters of the model. Lastly, we demonstrate the effectiveness of the adjoint diffusion solvers onthe face morphing problem., Comment: Initial pre-print

We introduces the Quantum-Train(QT) framework, a novel approach that integrates quantum computing with classical machine learning algorithms to address significant challenges in data encoding, model compression, and inference hardware requirements. Even with a slight decrease in accuracy, QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model, which significantly reduces the parameter count from $M$ to $O(\text{polylog} (M))$ during training. Our experiments demonstrate QT's effectiveness in classification tasks, offering insights into its potential to revolutionize machine learning by leveraging quantum computational advantages. This approach not only improves model efficiency but also reduces generalization errors, showcasing QT's potential across various machine learning applications., Comment: 12 pages, 6 figures

This work studies sparse adversarial perturbations bounded by $l_0$ norm. We propose a white-box PGD-like attack method named sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine sparse-PGD with a black-box attack to comprehensively and more reliably evaluate the models' robustness against $l_0$ bounded adversarial perturbations. Moreover, the efficiency of sparse-PGD enables us to conduct adversarial training to build robust models against sparse perturbations. Extensive experiments demonstrate that our proposed attack algorithm exhibits strong performance in different scenarios. More importantly, compared with other robust models, our adversarially trained model demonstrates state-of-the-art robustness against various sparse attacks. Codes are available at https://github.com/CityU-MLO/sPGD.

Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted scenarios where labeled training data is generally unavailable. To solve the problem, existing label-free methods leverage a few pairwise unlabeled data to distill the knowledge by aligning features or statistics between the source and target modalities. For instance, one typically aims to minimize the L2 distance or contrastive loss between the learned features of pairs of samples in the source (e.g. image) and the target (e.g. sketch) modalities. However, most algorithms in this domain only focus on the experimental results but lack theoretical insight. To bridge the gap between the theory and practical method of cross-modality distillation, we first formulate a general framework of cross-modality contrastive distillation (CMCD), built upon contrastive learning that leverages both positive and negative correspondence, towards a better distillation of generalizable features. Furthermore, we establish a thorough convergence analysis that reveals that the distance between source and target modalities significantly impacts the test error on downstream tasks within the target modality which is also validated by the empirical results. Extensive experimental results show that our algorithm outperforms existing algorithms consistently by a margin of 2-3\% across diverse modalities and tasks, covering modalities of image, sketch, depth map, and audio and tasks of recognition and segmentation.

There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact operational reliability. While a data-driven intrusion detection system (IDS) can potentially thwart attacks during deployment, also known as the evasion attack, the training of the detection algorithm may be corrupted by adversarial data injected into the database, also known as the poisoning attack. In this paper, we propose the first framework of IDS that is robust against joint poisoning and evasion attacks. We formulate the defense mechanism as a bilevel optimization, where the inner and outer levels deal with attacks that occur during training time and testing time, respectively. We verify the robustness of our method on the IEEE-13 bus feeder model against a diverse set of poisoning and evasion attack scenarios. The results indicate that our proposed method outperforms the baseline technique in terms of accuracy, precision, and recall for intrusion detection.

Large language models have shown their ability to become effective few-shot learners with prompting, revoluting the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt initialization, and always exhibits large variability among different runs. Such property makes prompt tuning highly unreliable and vulnerable to poorly constructed prompts, which limits its extension to more real-world applications. To tackle this issue, we propose to treat the hard prompt and soft prompt as separate inputs to mitigate noise brought by the prompt initialization. Furthermore, we optimize soft prompts with contrastive learning for utilizing class-aware information in the training process to maintain model performance. Experimental results demonstrate that \sysname outperforms state-of-the-art methods by 7.20% in accuracy and reduces the standard deviation by 2.02 on average. Furthermore, extensive experiments underscore its robustness and stability across 7 datasets covering various tasks., Comment: Submitted to ACL 2024

In many social networks, one publishes information that one wants to reveal (e.g., the photograph of some friends) together with information that may lead to privacy breaches (e.g., the name of these people). One might want to hide this sensitive information by encrypting it and sharing the decryption key only with trusted people, but this might not be enough. If the cipher associated to a face is always the same, correlation between the output of a face recognition system and the cipher can give useful clues and help train recognizers to identify untagged instances of the face. We refer to these as "correlation attacks". In this paper we present a coding system that attempts to counter correlation attacks by associating to each instance of a face a different encryption of the same tag in such a way that the correlation between different instances is minimal. In addition, we present a key distribution code that allows only the owner of the images to encode the tags, but allows a group of trusted friends to decode them.

Semantic communication (SemCom) has emerged as a key technology for the forthcoming sixth-generation (6G) network, attributed to its enhanced communication efficiency and robustness against channel noise. However, the open nature of wireless channels renders them vulnerable to eavesdropping, posing a serious threat to privacy. To address this issue, we propose a novel secure semantic communication (SemCom) approach for image transmission, which integrates steganography technology to conceal private information within non-private images (host images). Specifically, we propose an invertible neural network (INN)-based signal steganography approach, which embeds channel input signals of a private image into those of a host image before transmission. This ensures that the original private image can be reconstructed from the received signals at the legitimate receiver, while the eavesdropper can only decode the information of the host image. Simulation results demonstrate that the proposed approach maintains comparable reconstruction quality of both host and private images at the legitimate receiver, compared to scenarios without any secure mechanisms. Experiments also show that the eavesdropper is only able to reconstruct host images, showcasing the enhanced security provided by our approach.

Face morphing attacks pose an increasing threat to face recognition (FR) systems. A morphed photo contains biometric information from two different subjects to take advantage of vulnerabilities in FRs. These systems are particularly susceptible to attacks when the morphs are subjected to print-scanning to mask the artifacts generated during the morphing process. We investigate the impact of print-scanning on morphing attack detection through a series of evaluations on heterogeneous morphing attack scenarios. Our experiments show that we can increase the Mated Morph Presentation Match Rate (MMPMR) by up to 8.48%. Furthermore, when a Single-image Morphing Attack Detection (S-MAD) algorithm is not trained to detect print-scanned morphs the Morphing Attack Classification Error Rate (MACER) can increase by up to 96.12%, indicating significant vulnerability., Comment: Accepted as a special sessions paper at IJCB 2024

Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a recently proposed morphing attack that has achieved state-of-the-art performance for representation-based morphing attacks. However, none of the existing research on DiMs have leveraged the iterative nature of DiMs and left the DiM model as a black box, treating it no differently than one would a Generative Adversarial Network (GAN) or Varational AutoEncoder (VAE). We propose a greedy strategy on the iterative sampling process of DiM models which searches for an optimal step guided by an identity-based heuristic function. We compare our proposed algorithm against ten other state-of-the-art morphing algorithms using the open-source SYN-MAD 2022 competition dataset. We find that our proposed algorithm is unreasonably effective, fooling all of the tested FR systems with an MMPMR of 100%, outperforming all other morphing algorithms compared., Comment: Accepted as a conference paper at IJCB 2024

Prior research has found that differences in the early period of neural network training significantly impact the performance of in-distribution (ID) tasks. However, neural networks are often sensitive to out-of-distribution (OOD) data, making them less reliable in downstream applications. Yet, the impact of the early training period on OOD generalization remains understudied due to its complexity and lack of effective analytical methodologies. In this work, we investigate the relationship between learning dynamics and OOD generalization during the early period of neural network training. We utilize the trace of Fisher Information and sharpness, with a focus on gradual unfreezing (i.e. progressively unfreezing parameters during training) as the methodology for investigation. Through a series of empirical experiments, we show that 1) selecting the number of trainable parameters at different times during training, i.e. realized by gradual unfreezing -- has a minuscule impact on ID results, but greatly affects the generalization to OOD data; 2) the absolute values of sharpness and trace of Fisher Information at the initial period of training are not indicative for OOD generalization, but the relative values could be; 3) the trace of Fisher Information and sharpness may be used as indicators for the removal of interventions during early period of training for better OOD generalization., Comment: WIP

For decades, aspects of the topological architecture, and of the mechanical as well as other physical behaviors of periodic lattice truss materials (PLTMs) have been massively studied. Their approximate infinite design space presents a double-edged sword, implying on one hand dramatic designability in fulfilling the requirement of various performance, but on the other hand unexpected intractability in determining the best candidate with tailoring properties. In recent years, the development of additive manufacturing and artificial intelligence spurs an explosion in the methods exploring the design space and searching its boundaries. However, regrettably, a normative description with sufficient information of PLTMs applying to machine learning has not yet been constructed, which confines the inverse design to some discrete and small scrutinized space. In the current paper, we develop a system of canonical descriptors for PLTMs, encoding not only the geometrical configurations but also mechanical properties into matrix forms to establish good quantitative correlations between structures and mechanical behaviors. The system mainly consists of the geometry matrix for the lattice node configuration, density, stretching and bending stiffness matrices for the lattice strut properties, as well as packing matrix for the principal periodic orientation. All these matrices are theoretically derived based on the intrinsic nature of PLTMs, leading to concise descriptions and sufficient information. The characteristics, including the completeness and uniqueness, of the descriptors are analyzed. In addition, we discuss how the current system of descriptors can be applied to the database construction and material discovery, and indicate the possible open problems., Comment: 57 pages, 7 figures, 3 tables

Affective Behavior Analysis aims to facilitate technology emotionally smart, creating a world where devices can understand and react to our emotions as humans do. To comprehensively evaluate the authenticity and applicability of emotional behavior analysis techniques in natural environments, the 6th competition on Affective Behavior Analysis in-the-wild (ABAW) utilizes the Aff-Wild2, Hume-Vidmimic2, and C-EXPR-DB datasets to set up five competitive tracks, i.e., Valence-Arousal (VA) Estimation, Expression (EXPR) Recognition, Action Unit (AU) Detection, Compound Expression (CE) Recognition, and Emotional Mimicry Intensity (EMI) Estimation. In this paper, we present our method designs for the five tasks. Specifically, our design mainly includes three aspects: 1) Utilizing a transformer-based feature fusion module to fully integrate emotional information provided by audio signals, visual images, and transcripts, offering high-quality expression features for the downstream tasks. 2) To achieve high-quality facial feature representations, we employ Masked-Auto Encoder as the visual features extraction model and fine-tune it with our facial dataset. 3) Considering the complexity of the video collection scenes, we conduct a more detailed dataset division based on scene characteristics and train the classifier for each scene. Extensive experiments demonstrate the superiority of our designs., Comment: 11 pages, 1 figure

Trajectory prediction is an essential component in autonomous driving, particularly for collision avoidance systems. Considering the inherent uncertainty of the task, numerous studies have utilized generative models to produce multiple plausible future trajectories for each agent. However, most of them suffer from restricted representation ability or unstable training issues. To overcome these limitations, we propose utilizing the diffusion model to generate the distribution of future trajectories. Two cruxes are to be settled to realize such an idea. First, the diversity of intention is intertwined with the uncertain surroundings, making the true distribution hard to parameterize. Second, the diffusion process is time-consuming during the inference phase, rendering it unrealistic to implement in a real-time driving system. We propose an Intention-aware denoising Diffusion Model (IDM), which tackles the above two problems. We decouple the original uncertainty into intention uncertainty and action uncertainty and model them with two dependent diffusion processes. To decrease the inference time, we reduce the variable dimensions in the intention-aware diffusion process and restrict the initial distribution of the action-aware diffusion process, which leads to fewer diffusion steps. To validate our approach, we conduct experiments on the Stanford Drone Dataset (SDD) and ETH/UCY dataset. Our methods achieve state-of-the-art results, with an FDE of 13.83 pixels on the SDD dataset and 0.36 meters on the ETH/UCY dataset. Compared with the original diffusion model, IDM reduces inference time by two-thirds. Interestingly, our experiments further reveal that introducing intention information is beneficial in modeling the diffusion process of fewer steps., Comment: 14 pages, 9 figures

Achieving high-performance computation on quantum systems presents a formidable challenge that necessitates bridging the capabilities between quantum hardware and classical computing resources. This study introduces an innovative distribution-aware Quantum-Classical-Quantum (QCQ) architecture, which integrates cutting-edge quantum software framework works with high-performance classical computing resources to address challenges in quantum simulation for materials and condensed matter physics. At the heart of this architecture is the seamless integration of VQE algorithms running on QPUs for efficient quantum state preparation, Tensor Network states, and QCNNs for classifying quantum states on classical hardware. For benchmarking quantum simulators, the QCQ architecture utilizes the cuQuantum SDK to leverage multi-GPU acceleration, integrated with PennyLane's Lightning plugin, demonstrating up to tenfold increases in computational speed for complex phase transition classification tasks compared to traditional CPU-based methods. This significant acceleration enables models such as the transverse field Ising and XXZ systems to accurately predict phase transitions with a 99.5% accuracy. The architecture's ability to distribute computation between QPUs and classical resources addresses critical bottlenecks in Quantum-HPC, paving the way for scalable quantum simulation. The QCQ framework embodies a synergistic combination of quantum algorithms, machine learning, and Quantum-HPC capabilities, enhancing its potential to provide transformative insights into the behavior of quantum systems across different scales. As quantum hardware continues to improve, this hybrid distribution-aware framework will play a crucial role in realizing the full potential of quantum computing by seamlessly integrating distributed quantum resources with the state-of-the-art classical computing infrastructure., Comment: 8 pages, 8 figures

In recent years, advanced deep neural networks have required a large number of parameters for training. Therefore, finding a method to reduce the number of parameters has become crucial for achieving efficient training. This work proposes a training scheme for classical neural networks (NNs) that utilizes the exponentially large Hilbert space of a quantum system. By mapping a classical NN with $M$ parameters to a quantum neural network (QNN) with $O(\text{polylog} (M))$ rotational gate angles, we can significantly reduce the number of parameters. These gate angles can be updated to train the classical NN. Unlike existing quantum machine learning (QML) methods, the results obtained from quantum computers using our approach can be directly used on classical computers. Numerical results on the MNIST and Iris datasets are presented to demonstrate the effectiveness of our approach. Additionally, we investigate the effects of deeper QNNs and the number of measurement shots for the QNN, followed by the theoretical perspective of the proposed method. This work opens a new branch of QML and offers a practical tool that can greatly enhance the influence of QML, as the trained QML results can benefit classical computing in our daily lives., Comment: 7 pages, 3 figures

We consider an optimization based limiter for enforcing positivity of internal energy in a semi-implicit scheme for solving gas dynamics equations. With Strang splitting, the compressible Navier-Stokes system is splitted into the compressible Euler equations, solved by the positivity-preserving Runge-Kutta discontinuous Galerkin (DG) method, and the parabolic subproblem, solved by Crank-Nicolson method with interior penalty DG method. Such a scheme is at most second order accurate in time, high order accurate in space, conservative, and preserves positivity of density. To further enforce the positivity of internal energy, we impose an optimization based limiter for the total energy variable to post process DG polynomial cell averages. The optimization based limiter can be efficiently implemented by the popular first order convex optimization algorithms such as the Douglas-Rachford splitting method if using the optimal algorithm parameters. Numerical tests suggest that the DG method with $\mathbb{Q}^k$ basis and the optimization-based limiter is robust for demanding low pressure problems such as high speed flows.

As humans advance toward a higher level of artificial intelligence, it is always at the cost of escalating computational resource consumption, which requires developing novel solutions to meet the exponential growth of AI computing demand. Neuromorphic hardware takes inspiration from how the brain processes information and promises energy-efficient computing of AI workloads. Despite its potential, neuromorphic hardware has not found its way into commercial AI data centers. In this article, we try to analyze the underlying reasons for this and derive requirements and guidelines to promote neuromorphic systems for efficient and sustainable cloud computing: We first review currently available neuromorphic hardware systems and collect examples where neuromorphic solutions excel conventional AI processing on CPUs and GPUs. Next, we identify applications, models and algorithms which are commonly deployed in AI data centers as further directions for neuromorphic algorithms research. Last, we derive requirements and best practices for the hardware and software integration of neuromorphic systems into data centers. With this article, we hope to increase awareness of the challenges of integrating neuromorphic hardware into data centers and to guide the community to enable sustainable and energy-efficient AI at scale., Comment: 11 pages, 2 figures, presented as poster at NICE 2024, 2nd version with updated author list and minor updates

Unmanned aerial vehicles (UAVs) are envisioned to provide diverse services from the air. The service quality may rely on the wireless performance which is affected by the UAV's position. In this paper, we focus on the UAV placement problem in the Internet of Vehicles, where the UAV is deployed to monitor the road traffic and sends the monitored videos to vehicles. The studied problem is formulated as video resolution maximization by optimizing over the UAV's position. Moreover, we take into account the maximal transmission delay and impose a probabilistic constraint. To solve the formulated problem, we first leverage the techniques in extreme value theory (EVT) and Gaussian process regression (GPR) to characterize the influence of the UAV's position on the delay performance. Based on this characterization, we subsequently propose a proactive resolution selection and UAV placement approach, which adaptively places the UAV according to the geographic distribution of vehicles. Numerical results justify the joint usage of EVT and GPR for maximal delay characterization. Through investigating the maximal transmission delay, the proposed approach nearly achieves the optimal performance when vehicles are evenly distributed, and reduces 10% and 19% of the 999-th 1000-quantile over two baselines when vehicles are biased distributed., Comment: Accepted in the IEEE Transactions on Intelligent Transportation Systems

Self-supervised methods have gained prominence in time series anomaly detection due to the scarcity of available annotations. Nevertheless, they typically demand extensive training data to acquire a generalizable representation map, which conflicts with scenarios of a few available samples, thereby limiting their performance. To overcome the limitation, we propose \textbf{AnomalyLLM}, a knowledge distillation-based time series anomaly detection approach where the student network is trained to mimic the features of the large language model (LLM)-based teacher network that is pretrained on large-scale datasets. During the testing phase, anomalies are detected when the discrepancy between the features of the teacher and student networks is large. To circumvent the student network from learning the teacher network's feature of anomalous samples, we devise two key strategies. 1) Prototypical signals are incorporated into the student network to consolidate the normal feature extraction. 2) We use synthetic anomalies to enlarge the representation gap between the two networks. AnomalyLLM demonstrates state-of-the-art performance on 15 datasets, improving accuracy by at least 14.5\% in the UCR dataset., Comment: 12 pages, 5 figures

Time series anomaly detection (TSAD) plays a vital role in various domains such as healthcare, networks, and industry. Considering labels are crucial for detection but difficult to obtain, we turn to TSAD with inexact supervision: only series-level labels are provided during the training phase, while point-level anomalies are predicted during the testing phase. Previous works follow a traditional multi-instance learning (MIL) approach, which focuses on encouraging high anomaly scores at individual time steps. However, time series anomalies are not only limited to individual point anomalies, they can also be collective anomalies, typically exhibiting abnormal patterns over subsequences. To address the challenge of collective anomalies, in this paper, we propose a tree-based MIL framework (TreeMIL). We first adopt an N-ary tree structure to divide the entire series into multiple nodes, where nodes at different levels represent subsequences with different lengths. Then, the subsequence features are extracted to determine the presence of collective anomalies. Finally, we calculate point-level anomaly scores by aggregating features from nodes at different levels. Experiments conducted on seven public datasets and eight baselines demonstrate that TreeMIL achieves an average 32.3% improvement in F1- score compared to previous state-of-the-art methods. The code is available at https://github.com/fly-orange/TreeMIL., Comment: This paper has been accepted by IEEE ICASSP 2024

The joint progress of artificial neural networks (ANNs) and domain specific hardware accelerators such as GPUs and TPUs took over many domains of machine learning research. This development is accompanied by a rapid growth of the required computational demands for larger models and more data. Concurrently, emerging properties of foundation models such as in-context learning drive new opportunities for machine learning applications. However, the computational cost of such applications is a limiting factor of the technology in data centers, and more importantly in mobile devices and edge systems. To mediate the energy footprint and non-trivial latency of contemporary systems, neuromorphic computing systems deeply integrate computational principles of neurobiological systems by leveraging low-power analog and digital technologies. SpiNNaker2 is a digital neuromorphic chip developed for scalable machine learning. The event-based and asynchronous design of SpiNNaker2 allows the composition of large-scale systems involving thousands of chips. This work features the operating principles of SpiNNaker2 systems, outlining the prototype of novel machine learning applications. These applications range from ANNs over bio-inspired spiking neural networks to generalized event-based neural networks. With the successful development and deployment of SpiNNaker2, we aim to facilitate the advancement of event-based and asynchronous algorithms for future generations of machine learning systems., Comment: Submitted at the Workshop on Machine Learning with New Compute Paradigms at NeurIPS 2023 (MLNPCP 2023)