Search

Topological structures reveal the hidden secrets and beauty in nature, such as the double helix in DNA, whilst, the manipula-tion of which in physical fields, especially in ultrafast struc-tured light, draw booming attention. Here we introduce a new family of spatiotemporal light fields, i.e. helical pulses, carry-ing sophisticated double-helix singularities in its electromag-netic topological structures. The helical pulses were solved from Maxwell's equation as chiral extensions of toroidal light pulses but with controlled angular momentum dependence. We unveil that the double helix singularities can maintain their topological invariance during propagation and the field exhibits paired generation and annihilation of vortices and antivortices in ultrafast space-time, so as to be potential information carriers beating previous conventional vortex structured light.

We present the theory of the longitudinal spin Seebeck effect between a Heisenberg spin-1/2 chain and a conductor. The effect consists of the generation of a spin current across the spin chain-conductor interface in response to the temperature difference between the two systems. In this setup, the current is given by the convolution of the local spin susceptibilities of the spin chain and the conductor. We find the spin current to be fully controlled, both in the magnitude and the sign, by the backscattering interaction between spinons, fractionalized spin excitations of the Heisenberg chain. In particular, it vanishes when the spinons form a non-interacting spinon gas. Our analytical results for the local spin susceptibility at the open end of the spin chain are in excellent agreement with numerical DMRG simulations.

A conjecture due to Y. Han asks whether that Hochschild homology groups of a finite dimensional algebra vanish for sufficiently large degrees would imply that the algebra is of finite global dimension. We investigate this conjecture from the viewpoint of recollements of derived categories. It is shown that for a recollement of unbounded derived categories of rings which extends downwards (or upwards) one step, Han's conjecture holds for the ring in the middle if and only if it holds for the two rings on the two sides and hence Han's conjecture is reduced to derived $2$-simple rings. Furthermore, this reduction result is applied to Han's conjecture for Morita contexts rings and exact contexts. Finally it is proved that Han's conjecture holds for skew-gentle algebras, category algebras of finite EI categories and Geiss-Leclerc-Schr\"{o}er algebras associated to Cartan triples., Comment: 14 pages. Comments are welcome!

The ubiquitous occurrence of toroidal vortices or vortex rings in fluid-dynamic scenarios in nature has garnered significant attention of scientific frontier, whilst, the electromagnetic counterparts of which were only proposed recently with two distinct manifestations: vector toroidal pulses [Nat. Photon. 16, 523 (2022)] and scalar phase toroidal vortices [Nat. Photon. 16, 519 (2022)]. This dichotomy in the understanding of toroidal vortex phenomena has prompted a reassessment of their fundamental nature. Herein, we theoretically propose a novel form of electromagnetic toroidal vortex solutions, that uniquely integrate both scalar and vector characteristics, challenging the prevailing notion of their mutual exclusivity. We also present the experimental generation of the hybrid toroidal vortex pulses by a compact coaxial horn emitter augmented with a metasurface. This methodology not only demonstrates the feasibility of creating such complex vortex structures but also endows the resulting pulses with unique properties, including the coexistence of transverse orbital angular momentum, electromagnetic vortex streets, and topological skyrmion textures. These attributes introduce new dimensions in topologically complex structured waves, opening avenues for enhanced free-space information transmission, topologically nontrivial light-matter interaction and microscopy techniques.

Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated. While traditional adversarial training (AT) techniques offer some resilience, they often focus on defending against a single type of attack, e.g., the $\ell_\infty$-norm attack, which can fail for other types. This paper introduces a computationally efficient multilevel $\ell_p$ defense, called the Efficient Robust Mode Connectivity (EMRC) method, which aims to enhance a deep learning model's resilience against multiple $\ell_p$-norm attacks. Similar to analytical continuation approaches used in continuous optimization, the method blends two $p$-specific adversarially optimal models, the $\ell_1$- and $\ell_\infty$-norm AT solutions, to provide good adversarial robustness for a range of $p$. We present experiments demonstrating that our approach performs better on various attacks as compared to AT-$\ell_\infty$, E-AT, and MSD, for datasets/architectures including: CIFAR-10, CIFAR-100 / PreResNet110, WideResNet, ViT-Base.

Convolutional neural networks (CNNs), one of the key architectures of deep learning models, have achieved superior performance on many machine learning tasks such as image classification, video recognition, and power systems. Despite their success, CNNs can be easily contaminated by natural noises and artificially injected noises such as backdoor attacks. In this paper, we propose a robust recovery method to remove the noise from the potentially contaminated CNNs and provide an exact recovery guarantee on one-hidden-layer non-overlapping CNNs with the rectified linear unit (ReLU) activation function. Our theoretical results show that both CNNs' weights and biases can be exactly recovered under the overparameterization setting with some mild assumptions. The experimental results demonstrate the correctness of the proofs and the effectiveness of the method in both the synthetic environment and the practical neural network setting. Our results also indicate that the proposed method can be extended to multiple-layer CNNs and potentially serve as a defense strategy against backdoor attacks.

Let $\mathbb{K}$ be a field of characteristic $p$ and $G$ be a cyclic $p$-group which acts on a finite acyclic quiver $Q$. The folding process associates a Cartan triple to the action. We establish a Morita equivalence between the skew group algebra of the preprojective algebra of $Q$ and the generalized preprojective algebra associated to the Cartan triple in the sense of Geiss, Leclerc and Schr\"{o}er. The Morita equivalence induces an isomorphism between certain ideal monoids of these preprojective algebras, which is compatible with the embedding of Weyl groups appearing in the folding process., Comment: 21 pages

Deep neural networks are susceptible to backdoor attacks, where adversaries manipulate model predictions by inserting malicious samples into the training data. Currently, there is still a lack of direct filtering methods for identifying suspicious training data to unveil potential backdoor samples. In this paper, we propose a novel method, Prediction Shift Backdoor Detection (PSBD), leveraging an uncertainty-based approach requiring minimal unlabeled clean validation data. PSBD is motivated by an intriguing Prediction Shift (PS) phenomenon, where poisoned models' predictions on clean data often shift away from true labels towards certain other labels with dropout applied during inference, while backdoor samples exhibit less PS. We hypothesize PS results from neuron bias effect, making neurons favor features of certain classes. PSBD identifies backdoor training samples by computing the Prediction Shift Uncertainty (PSU), the variance in probability values when dropout layers are toggled on and off during model inference. Extensive experiments have been conducted to verify the effectiveness and efficiency of PSBD, which achieves state-of-the-art results among mainstream detection methods.

Quality-Diversity (QD) algorithms have emerged as a powerful optimization paradigm with the aim of generating a set of high-quality and diverse solutions. To achieve such a challenging goal, QD algorithms require maintaining a large archive and a large population in each iteration, which brings two main issues, sample and resource efficiency. Most advanced QD algorithms focus on improving the sample efficiency, while the resource efficiency is overlooked to some extent. Particularly, the resource overhead during the training process has not been touched yet, hindering the wider application of QD algorithms. In this paper, we highlight this important research question, i.e., how to efficiently train QD algorithms with limited resources, and propose a novel and effective method called RefQD to address it. RefQD decomposes a neural network into representation and decision parts, and shares the representation part with all decision parts in the archive to reduce the resource overhead. It also employs a series of strategies to address the mismatch issue between the old decision parts and the newly updated representation part. Experiments on different types of tasks from small to large resource consumption demonstrate the excellent performance of RefQD: it not only uses significantly fewer resources (e.g., 16\% GPU memories on QDax and 3.7\% on Atari) but also achieves comparable or better performance compared to sample-efficient QD algorithms. Our code is available at \url{https://github.com/lamda-bbo/RefQD}., Comment: ICML 2024

Recent advancements in optical, terahertz, and microwave systems have unveiled non-transverse optical toroidal pulses characterized by skyrmionic topologies, fractal-like singularities, space-time nonseparability, and anapole-exciting ability. Despite this, the longitudinally polarized fields of canonical toroidal pulses notably lag behind their transverse counterparts in magnitude. Interestingly, although mushroom-cloud-like toroidal vortices with strong longitudinal fields are common in nature, they remain unexplored in the realm of electromagnetics. Here, we present strongly longitudinally polarized toroidal pulses (SLPTPs) which boast a longitudinal component amplitude exceeding that of the transverse component by over tenfold. This unique polarization property endows SLPTPs with robust propagation characteristics, showcasing nondiffracting behavior. The propagation-invariant strongly longitudinally polarized field holds promise for pioneering light-matter interactions, far-field superresolution microscopy, and high-capacity wireless communication utilizing three polarizations.

The fundamental principle of satellite or node-based positioning involves triangulating the receiver's coordinates through the intersection of spatial distances. Recent advancements in hybrid wireless networks have yielded high-precision positioning at decimetre-level (wavelength-level) (Nature 611, 473-478 (2022)), approaching the resolution limits in free space. Here, we present a three-dimensional (3D) super-resolution positioning paradigm in free space by utilizing a novel kind of topologically structured pulses, toroidal electromagnetic pulses (Nat. Photonics 16(7), 523-528 (2022); Sci. Adv. 10(2), eadl1803 (2024)). Excited by the recent compact generator of toroidal pulses and their sophisticated topological and nonseparable structures, we demonstrate that the space-time nonseparability and skyrmion topology inherent in toroidal pulses can be harnessed to achieve freespace microwave 3D positioning with super-resolution accuracy, reaching the centimeter level, using a single emitting antenna. This work opens up new avenues for exploring the potential applications of topological electromagnetic pulses including but not limited to positioning, imaging, and sensing technologies.

We present an asymptotic analysis of a stochastic two-compartmental cell proliferation system with regulatory mechanisms. We model the system as a state-dependent birth and death process. Proliferation of hematopoietic stem cells (HSCs) is regulated by population density of HSC-derived clones and differentiation of HSC is regulated by population density of HSCs. By scaling up the initial population, we show the density of dynamics converges in distribution to the solution of a system of ordinary differential equations (ODEs). The system of ODEs has a unique non-trivial equilibrium that is globally stable. Furthermore, we show the scaled fluctuation of the population converges in law to a linear diffusion with time-dependent coefficients. With initial data being Gaussian, the limit is a Gauss-Markov process, and it behaves like the FCLT limit under equilibrium with constant coefficients at large times. This is proved by establishing exponential convergence in the 2-Wasserstein metric for the associated Gaussian measures in a $\mathcal{L}_2$ Hilbert space. We apply our results to analyze and compare two regulatory mechanisms in the hematopoietic system. Simulations are conducted to verify our large-scale and long-time approximation of the dynamics. We demonstrate some regulatory mechanisms are efficient (converge to steady state rapidly) but not effective (have large fluctuation around the steady state).

Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application. The detection of these attacks is crucial for maintaining the reliability and security of GNN classification tasks, but effective detection techniques are lacking. Following an initial investigation, we observed that while graph-level explanations can offer limited insights, their effectiveness in detecting backdoor triggers is inconsistent and incomplete. To bridge this gap, we extract and transform secondary outputs of GNN explanation mechanisms, designing seven novel metrics that more effectively detect backdoor attacks. Additionally, we develop an adaptive attack to rigorously evaluate our approach. We test our method on multiple benchmark datasets and examine its efficacy against various attack models. Our results show that our method can achieve high detection performance, marking a significant advancement in safeguarding GNNs against backdoor attacks.

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily focused on the identification of backdoored models or poisoned data characteristics, typically operating under the assumption of access to clean data. In this work, we delve into a relatively underexplored challenge: the automatic identification of backdoor data within a poisoned dataset, all under realistic conditions, i.e., without the need for additional clean data or without manually defining a threshold for backdoor detection. We draw an inspiration from the scaled prediction consistency (SPC) technique, which exploits the prediction invariance of poisoned data to an input scaling factor. Based on this, we pose the backdoor data identification problem as a hierarchical data splitting optimization problem, leveraging a novel SPC-based loss function as the primary optimization objective. Our innovation unfolds in several key aspects. First, we revisit the vanilla SPC method, unveiling its limitations in addressing the proposed backdoor identification problem. Subsequently, we develop a bi-level optimization-based approach to precisely identify backdoor data by minimizing the advanced SPC loss. Finally, we demonstrate the efficacy of our proposal against a spectrum of backdoor attacks, encompassing basic label-corrupted attacks as well as more sophisticated clean-label attacks, evaluated across various benchmark datasets. Experiment results show that our approach often surpasses the performance of current baselines in identifying backdoor data points, resulting in about 4%-36% improvement in average AUROC. Codes are available at https://github.com/OPTML-Group/BackdoorMSPC., Comment: The Twelfth International Conference on Learning Representations (ICLR 2024)

The simultaneous localization and recognition of subwavelength non-cooperative entities within complex multi-scattering environments using a simplified system continues to pose a substantial challenge. This letter addresses this challenge by synergistically integrating time reversal time-frequency phase prints (TRTFPPs) and neural networks. Initially, a time reversal (TR) single-input single-output (SISO) framework is employed to generate TRTFPPs. To enhance the models' adaptability, particularly in the presence of noise, data augmentation techniques are applied. Subsequently, neural networks are employed to comprehend the TRTFPPs. Specifically, a cascaded neural network structure is embraced, encompassing both a recognition neural network and distinct neural networks for localizing different entities. Through the devised approach, two types of subwavelength entities are successfully identified and precisely localized through numerical simulations and experimental verification in laboratory environment. The proposed methodology holds applicability across various electromagnetic systems, including but not limited to detection, imaging, human-computer interaction, and the Internet of Things (IoT).

Uncertainty estimation plays a pivotal role in ensuring the reliability of safety-critical human-AI interaction systems, particularly in the medical domain. However, a general method for quantifying the uncertainty of free-form answers has yet to be established in open-ended medical question-answering (QA) tasks, where irrelevant words and sequences with limited semantic information can be the primary source of uncertainty due to the presence of generative inequality. In this paper, we propose the Word-Sequence Entropy (WSE), which calibrates the uncertainty proportion at both the word and sequence levels according to the semantic relevance, with greater emphasis placed on keywords and more relevant sequences when performing uncertainty quantification. We compare WSE with 6 baseline methods on 5 free-form medical QA datasets, utilizing 7 "off-the-shelf" large language models (LLMs), and show that WSE exhibits superior performance on accurate uncertainty measurement under two standard criteria for correctness evaluation (e.g., WSE outperforms existing state-of-the-art method by 3.23% AUROC on the MedQA dataset). Additionally, in terms of the potential for real-world medical QA applications, we achieve a significant enhancement in the performance of LLMs when employing sequences with lower uncertainty, identified by WSE, as final answers (e.g., +6.36% accuracy improvement on the COVID-QA dataset), without requiring any additional task-specific fine-tuning or architectural modifications., Comment: 18 pages

With the advent of byte-addressable memory devices, such as CXL memory, persistent memory, and storage-class memory, tiered memory systems have become a reality. Page migration is the de facto method within operating systems for managing tiered memory. It aims to bring hot data whenever possible into fast memory to optimize the performance of data accesses while using slow memory to accommodate data spilled from fast memory. While the existing research has demonstrated the effectiveness of various optimizations on page migration, it falls short of addressing a fundamental question: Is exclusive memory tiering, in which a page is either present in fast memory or slow memory, but not both simultaneously, the optimal strategy for tiered memory management? We demonstrate that page migration-based exclusive memory tiering suffers significant performance degradation when fast memory is under pressure. In this paper, we propose non-exclusive memory tiering, a page management strategy that retains a copy of pages recently promoted from slow memory to fast memory to mitigate memory thrashing. To enable non-exclusive memory tiering, we develop Nomad, a new page management mechanism for Linux that features transactional page migration and page shadowing. Nomad helps remove page migration off the critical path of program execution and makes migration completely asynchronous. Evaluations with carefully crafted micro-benchmarks and real-world applications show that Nomad is able to achieve up to 6x performance improvement over the state-of-the-art transparent page placement (TPP) approach in Linux when under memory pressure. We also compare Nomad with a recently proposed hardware-assisted, access sampling-based page migration approach and demonstrate Nomad's strengths and potential weaknesses in various scenarios.

Quality-Diversity (QD) algorithms are a new type of Evolutionary Algorithms (EAs), aiming to find a set of high-performing, yet diverse solutions. They have found many successful applications in reinforcement learning and robotics, helping improve the robustness in complex environments. Furthermore, they often empirically find a better overall solution than traditional search algorithms which explicitly search for a single highest-performing solution. However, their theoretical analysis is far behind, leaving many fundamental questions unexplored. In this paper, we try to shed some light on the optimization ability of QD algorithms via rigorous running time analysis. By comparing the popular QD algorithm MAP-Elites with $(\mu+1)$-EA (a typical EA focusing on finding better objective values only), we prove that on two NP-hard problem classes with wide applications, i.e., monotone approximately submodular maximization with a size constraint, and set cover, MAP-Elites can achieve the (asymptotically) optimal polynomial-time approximation ratio, while $(\mu+1)$-EA requires exponential expected time on some instances. This provides theoretical justification for that QD algorithms can be helpful for optimization, and discloses that the simultaneous search for high-performing solutions with diverse behaviors can provide stepping stones to good overall solutions and help avoid local optima., Comment: The conference version of this paper has appeared at IJCAI'24. This version contains all the proof details

This paper uses Physics-Informed Neural Network (PINN) to design Frequency Selective Surface (FSS). PINN integrates physical information into the loss function, so training PINN does not require a dataset, which will be faster than traditional neural networks for inverse design. The specific implementation process of this paper is to construct a PINN using field solutions of mode matching method, and given the design goal, the PINN can train the shape of the diaphragms. The single frequency FSS that meets the design goal was designed using the inverse design method proposed in this paper without a dataset, verifying the rationality of using PINN to design metasurface. Using PINN for inverse design is not limited to single frequency FSS, but can also be used for more complex metasurface.

This paper addresses the challenge of transient stability in power systems with missing parameters and uncertainty propagation in swing equations. We introduce a novel application of Physics-Informed Neural Networks (PINNs), specifically an Ensemble of PINNs (E-PINNs), to estimate critical parameters like rotor angle and inertia coefficient with enhanced accuracy and reduced computational load. E-PINNs capitalize on the underlying physical principles of swing equations to provide a robust solution. Our approach not only facilitates efficient parameter estimation but also quantifies uncertainties, delivering probabilistic insights into the system behavior. The efficacy of E-PINNs is demonstrated through the analysis of $1$-bus and $2$-bus systems, highlighting the model's ability to handle parameter variability and data scarcity. The study advances the application of machine learning in power system stability, paving the way for reliable and computationally efficient transient stability analysis.

Toroidal electromagnetic pulses have been recently reported as nontransverse, space-time nonseparable topological excitations of free space [Nat. Photon. 16, 523-528 (2022)]. However, their propagation dynamics and topological configurations have not been comprehensively experimentally characterized. Here, we report that microwave toroidal pulses can be launched by a broadband conical horn antenna. We experimentally map their skyrmionic textures and demonstrate how that during propagation the pulses evolves towards stronger space-time nonseparability and closer proximity to the canonical Hellwarth and Nouchi toroidal pulses.

Recent multi-view subspace clustering achieves impressive results utilizing deep networks, where the self-expressive correlation is typically modeled by a fully connected (FC) layer. However, they still suffer from two limitations. i) The parameter scale of the FC layer is quadratic to sample numbers, resulting in high time and memory costs that significantly degrade their feasibility in large-scale datasets. ii) It is under-explored to extract a unified representation that simultaneously satisfies minimal sufficiency and discriminability. To this end, we propose a novel deep framework, termed Efficient and Effective deep Multi-View Subspace Clustering (E$^2$MVSC). Instead of a parameterized FC layer, we design a Relation-Metric Net that decouples network parameter scale from sample numbers for greater computational efficiency. Most importantly, the proposed method devises a multi-type auto-encoder to explicitly decouple consistent, complementary, and superfluous information from every view, which is supervised by a soft clustering assignment similarity constraint. Following information bottleneck theory and the maximal coding rate reduction principle, a sufficient yet minimal unified representation can be obtained, as well as pursuing intra-cluster aggregation and inter-cluster separability within it. Extensive experiments show that E$^2$MVSC yields comparable results to existing methods and achieves state-of-the-art performance in various types of multi-view datasets.

Diversity plays a significant role in many problems, such as ensemble learning, reinforcement learning, and combinatorial optimization. How to define the diversity measure is a longstanding problem. Many methods rely on expert experience to define a proper behavior space and then obtain the diversity measure, which is, however, challenging in many scenarios. In this paper, we propose the problem of learning a behavior space from human feedback and present a general method called Diversity from Human Feedback (DivHF) to solve it. DivHF learns a behavior descriptor consistent with human preference by querying human feedback. The learned behavior descriptor can be combined with any distance measure to define a diversity measure. We demonstrate the effectiveness of DivHF by integrating it with the Quality-Diversity optimization algorithm MAP-Elites and conducting experiments on the QDax suite. The results show that DivHF learns a behavior space that aligns better with human requirements compared to direct data-driven approaches and leads to more diverse solutions under human preference. Our contributions include formulating the problem, proposing the DivHF method, and demonstrating its effectiveness through experiments.

Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new tasks. Existing schemes solve it by enhancing the mutual-exclusivity or diversity of training samples, but these data manipulation strategies are data-dependent and insufficiently flexible. This work alleviates overfitting in meta-learning from the perspective of gradient regularization and proposes a data-independent \textbf{M}eta-\textbf{G}radient \textbf{Aug}mentation (\textbf{MGAug}) method. The key idea is to first break the rote memories by network pruning to address memorization overfitting in the inner loop, and then the gradients of pruned sub-networks naturally form the high-quality augmentation of the meta-gradient to alleviate learner overfitting in the outer loop. Specifically, we explore three pruning strategies, including \textit{random width pruning}, \textit{random parameter pruning}, and a newly proposed \textit{catfish pruning} that measures a Meta-Memorization Carrying Amount (MMCA) score for each parameter and prunes high-score ones to break rote memories as much as possible. The proposed MGAug is theoretically guaranteed by the generalization bound from the PAC-Bayes framework. In addition, we extend a lightweight version, called MGAug-MaxUp, as a trade-off between performance gains and resource overhead. Extensive experiments on multiple few-shot learning benchmarks validate MGAug's effectiveness and significant improvement over various meta-baselines. The code is publicly available at \url{https://github.com/xxLifeLover/Meta-Gradient-Augmentation}.

As semiconductor power density is no longer constant with the technology process scaling down, modern CPUs are integrating capable data accelerators on chip, aiming to improve performance and efficiency for a wide range of applications and usages. One such accelerator is the Intel Data Streaming Accelerator (DSA) introduced in Intel 4th Generation Xeon Scalable CPUs (Sapphire Rapids). DSA targets data movement operations in memory that are common sources of overhead in datacenter workloads and infrastructure. In addition, it becomes much more versatile by supporting a wider range of operations on streaming data, such as CRC32 calculations, delta record creation/merging, and data integrity field (DIF) operations. This paper sets out to introduce the latest features supported by DSA, deep-dive into its versatility, and analyze its throughput benefits through a comprehensive evaluation. Along with the analysis of its characteristics, and the rich software ecosystem of DSA, we summarize several insights and guidelines for the programmer to make the most out of DSA, and use an in-depth case study of DPDK Vhost to demonstrate how these guidelines benefit a real application., Comment: This paper has been accepted by ASPLOS'24. Please refer to the linked DOI for the official version of this paper

The ever-growing demands for memory with larger capacity and higher bandwidth have driven recent innovations on memory expansion and disaggregation technologies based on Compute eXpress Link (CXL). Especially, CXL-based memory expansion technology has recently gained notable attention for its ability not only to economically expand memory capacity and bandwidth but also to decouple memory technologies from a specific memory interface of the CPU. However, since CXL memory devices have not been widely available, they have been emulated using DDR memory in a remote NUMA node. In this paper, for the first time, we comprehensively evaluate a true CXL-ready system based on the latest 4th-generation Intel Xeon CPU with three CXL memory devices from different manufacturers. Specifically, we run a set of microbenchmarks not only to compare the performance of true CXL memory with that of emulated CXL memory but also to analyze the complex interplay between the CPU and CXL memory in depth. This reveals important differences between emulated CXL memory and true CXL memory, some of which will compel researchers to revisit the analyses and proposals from recent work. Next, we identify opportunities for memory-bandwidth-intensive applications to benefit from the use of CXL memory. Lastly, we propose a CXL-memory-aware dynamic page allocation policy, Caption to more efficiently use CXL memory as a bandwidth expander. We demonstrate that Caption can automatically converge to an empirically favorable percentage of pages allocated to CXL memory, which improves the performance of memory-bandwidth-intensive applications by up to 24% when compared to the default page allocation policy designed for traditional NUMA systems., Comment: This paper has been accepted by MICRO'23. Please refer to the https://doi.org/10.1145/3613424.3614256 for the official version of this paper

Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase. Recent studies have shown that despite the success of improving adversarial robustness against a single type of attack using robust training techniques, models are still vulnerable to diversified $\ell_p$ attacks. To achieve diversified $\ell_p$ robustness, we propose a novel robust mode connectivity (RMC)-oriented adversarial defense that contains two population-based learning phases. The first phase, RMC, is able to search the model parameter space between two pre-trained models and find a path containing points with high robustness against diversified $\ell_p$ attacks. In light of the effectiveness of RMC, we develop a second phase, RMC-based optimization, with RMC serving as the basic unit for further enhancement of neural network diversified $\ell_p$ robustness. To increase computational efficiency, we incorporate learning with a self-robust mode connectivity (SRMC) module that enables the fast proliferation of the population used for endpoints of RMC. Furthermore, we draw parallels between SRMC and the human immune system. Experimental results on various datasets and model architectures demonstrate that the proposed defense methods can achieve high diversified $\ell_p$ robustness against $\ell_\infty$, $\ell_2$, $\ell_1$, and hybrid attacks. Codes are available at \url{https://github.com/wangren09/MCGR}.

Existing electromagnetic inverse design methods are often established in the spacial domain. This communication presents an inverse design method, which can design aperture field for the desired phaseless radiation pattern, from the spectral domain perspective. In addition, it naturally adapts to the polarization constraint. Specifically, the inverse design can be converted into solving the first kind of Fredholm integral equation, using the spectral domain method. To deal with the ill-posedness of such integral equation, we apply modal expansion to the integrand. To cope with the non-linearity introduced by phaseless, we use a multi-objective optimization algorithm to obtain the coefficients in the modal expansion. Finally, we use this method to break the cosine rule that the directivity of 2D arrays drops as cosine of the angle, which is a puzzle in wide-angle scanning. The numerical simulation results meet expectations and illustrate the feasibility of the method.

Existing multi-view representation learning methods typically follow a specific-to-uniform pipeline, extracting latent features from each view and then fusing or aligning them to obtain the unified object representation. However, the manually pre-specify fusion functions and view-private redundant information mixed in features potentially degrade the quality of the derived representation. To overcome them, we propose a novel bi-level-optimization-based multi-view learning framework, where the representation is learned in a uniform-to-specific manner. Specifically, we train a meta-learner, namely MetaViewer, to learn fusion and model the view-shared meta representation in outer-level optimization. Start with this meta representation, view-specific base-learners are then required to rapidly reconstruct the corresponding view in inner-level. MetaViewer eventually updates by observing reconstruction processes from uniform to specific over all views, and learns an optimal fusion scheme that separates and filters out view-private information. Extensive experimental results in downstream tasks such as classification and clustering demonstrate the effectiveness of our method., Comment: 8 pages, 5 figures, conference

Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and challenging as large inter-class ambiguities among fine-grained classes cause more noisy labels. We empirically show that existing methods that work well for LNL fail to achieve satisfying performance for LNL-FG, arising the practical need of effective solutions for LNL-FG. To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation. Specifically, we design a noise-tolerated supervised contrastive learning loss that incorporates a weight-aware mechanism for noisy label correction and selectively updating momentum queue lists. By this mechanism, we mitigate the effects of noisy anchors and avoid inserting noisy labels into the momentum-updated queue. Besides, to avoid manually-defined augmentation strategies in contrastive learning, we propose an efficient stochastic module that samples feature embeddings from a generated distribution, which can also enhance the representation ability of deep models. SNSCL is general and compatible with prevailing robust LNL strategies to improve their performance for LNL-FG. Extensive experiments demonstrate the effectiveness of SNSCL., Comment: Accepted to CVPR 2023

We consider a time-continuous Markov branching process of proliferating cells with a countable collection of types. Among-type transitions are inspired by the Tug-of-War process introduced in McFarland et al. as a mathematical model for competition of advantageous driver mutations and deleterious passenger mutations in cancer cells. We introduce a version of the model in which a driver mutation pushes the type of the cell $L$-units up, while a passenger mutation pulls it $1$-unit down. The distribution of time to divisions depends on the type (fitness) of cell, which is an integer. The extinction probability given any initial cell type is strictly less than $1$, which allows us to investigate the transition between types (type transition) in an infinitely long cell lineage of cells. The analysis leads to the result that under driver dominance, the type transition process escapes to infinity, while under passenger dominance, it leads to a limit distribution. Implications in cancer cell dynamics and population genetics are discussed.

Full-system simulation of computer systems is critical to capture the complex interplay between various hardware and software components in future systems. Modeling the network subsystem is indispensable to the fidelity of the full-system simulation due to the increasing importance of scale-out systems. The network software stack has undergone major changes over the last decade, and kernel-bypass networking stacks and data-plane networks are rapidly replacing the conventional kernel network stack. Nevertheless, the current state-of-the-art architectural simulators still use kernel networking which precludes realistic network application scenarios. In this work, we enable kernel bypass networking stack on gem5, the state-of-the-art full-system architectural simulator. We extend gem5's NIC hardware model and device driver to enable the support for userspace device drivers to run the DPDK framework. We also implement a network load generator hardware model in gem5 to generate various traffic patterns and perform per-packet timestamp and latency measurements without introducing packet loss. Our experimental results show that DPDK's simulated network bandwidth scales with the number of cores and NIC ports. As two use cases, we analyze the sensitivity of (1) network performance to several microarchitectural parameters, and (2) direct cache access (DCA) technology to DPDK burst size., Comment: 4 Pages, 4 Figures and 1 Table

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high clean accuracy in downstream tasks. The stealthiness of backdoor attacks has imposed tremendous defense challenges in today's machine learning paradigm. In this paper, we explore the potential of self-training via additional unlabeled data for mitigating backdoor attacks. We begin by making a pilot study to show that vanilla self-training is not effective in backdoor mitigation. Spurred by that, we propose to defend the backdoor attacks by leveraging strong but proper data augmentations in the self-training pseudo-labeling stage. We find that the new self-training regime help in defending against backdoor attacks to a great extent. Its effectiveness is demonstrated through experiments for different backdoor triggers on CIFAR-10 and a combination of CIFAR-10 with an additional unlabeled 500K TinyImages dataset. Finally, we explore the direction of combining self-supervised representation learning with self-training for further improvement in backdoor defense., Comment: Accepted at SafeAI 2023: AAAI's Workshop on Artificial Intelligence Safety