Search arXiv⌕ Search

arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 505 records · Page 28Linked to original sources
arXiv2023

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization

Adversarial training is one of the best-performing methods in improving the robustness of deep language models. However, robust models come at the cost of high time consumption, as they require multi-step gradient ascents or word substitutions to obtain adversarial samples. In addition, these generated samples are deficient in grammatical quality and semantic consistency, which impairs the effectiveness of adversarial training. To address these problems, we introduce a novel, effective procedure for instead adversarial training with only clean data. Our procedure, distribution shift risk minimization (DSRM), estimates the adversarial loss by perturbing the input data's probability distribution rather than their embeddings. This formulation results in a robust model that minimizes the expected global loss under adversarial attacks. Our approach requires zero adversarial samples for training and reduces time consumption by up to 70\% compared to current best-performing adversarial training methods. Experiments demonstrate that DSRM considerably improves BERT's resistance to textual adversarial attacks and achieves state-of-the-art robust accuracy on various benchmarks.

cs.CL↗
arXiv2023

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees

In this work, we introduce a new variant of online gradient descent, which provably converges to Nash Equilibria and simultaneously attains sublinear regret for the class of congestion games in the semi-bandit feedback setting. Our proposed method admits convergence rates depending only polynomially on the number of players and the number of facilities, but not on the size of the action set, which can be exponentially large in terms of the number of facilities. Moreover, the running time of our method has polynomial-time dependence on the implicit description of the game. As a result, our work answers an open question from (Du et. al, 2022).

cs.GT↗
arXiv2023

On Fan's conjecture about $4$-flow

Let $G$ be a bridgeless graph, $C$ is a circuit of $G$. Fan proposed a conjecture that if $G/C$ admits a nowhere-zero 4-flow, then $G$ admits a 4-flow $(D,f)$ such that $E(G)-E(C)\subseteq$ supp$(f)$ and $|\textrm{supp}(f)\cap E(C)|>\frac{3}{4}|E(C)|$. The purpose of this conjecture is to find shorter circuit cover in bridgeless graphs. Fan showed that the conjecture holds for $|E(C)|\le19.$ Wang, Lu and Zhang showed that the conjecture holds for $|E(C)|\le 27$. In this paper, we prove that the conjecture holds for $|E(C)|\le 35.$

math.CO↗
arXiv2023

Stability and fine structure of symmetry-enriched quantum criticality in a spin ladder triangular model

In this letter, we propose and study a ladder triangular cluster model which possesses a $\mathbb{Z}_2$ symmetry and an anti-unitary $\mathbb{Z}^{\mathbb{T}}_2$ symmetry generated by the spin-flip and complex conjugation, respectively. The phase diagram of the model hosts a critical line between a spontaneous symmetry breaking phase and a symmetry protected topological phase. Along the critical line, one endpoint exhibits symmetry-enriched Ashkin-Teller universality (SEATU), while other critical points fall into the symmetry-enriched Ising universality (SEIU). Both universality classes accommodate symmetry protected degenerate edge modes under open boundary conditions. This degeneracy can be lifted with a gap opening when proper perturbation is applied to the boundary. With system size ($L$) increasing, at the point of SEATU, the gap closes following $L^{-1}$. In contrast, for the critical points of SEIU apart from a point with the known gap closing as $L^{-14}$, other points surprisingly show exponentially gap closing. The coexistence of different gap closing behaviors for critical points of the same symmetry-enriched universality goes beyond the the usual understanding of symmetry-enriched universality class, implying a fine and rich structure of phase transition and universality class.

cond-mat.str-el↗
arXiv2023

Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs

Real-world graphs generally have only one kind of tendency in their connections. These connections are either homophily-prone or heterophily-prone. While graphs with homophily-prone edges tend to connect nodes with the same class (i.e., intra-class nodes), heterophily-prone edges tend to build relationships between nodes with different classes (i.e., inter-class nodes). Existing GNNs only take the original graph during training. The problem with this approach is that it forgets to take into consideration the ``missing-half" structural information, that is, heterophily-prone topology for homophily-prone graphs and homophily-prone topology for heterophily-prone graphs. In our paper, we introduce Graph cOmplementAry Learning, namely GOAL, which consists of two components: graph complementation and complemented graph convolution. The first component finds the missing-half structural information for a given graph to complement it. The complemented graph has two sets of graphs including both homophily- and heterophily-prone topology. In the latter component, to handle complemented graphs, we design a new graph convolution from the perspective of optimisation. The experiment results show that GOAL consistently outperforms all baselines in eight real-world datasets.

cs.SI↗
arXiv2023

Flat band-engineered spin-density wave and the emergent multi-$k$ magnetic state in the topological kagome metal Mn$_{3}$Sn

Magnetic kagome metals, in which topologically non-trivial band structures and electronic correlation are intertwined, have recently emerged as an exciting platform to explore exotic correlated topological phases, that are usually not found in weakly interacting materials described within the semi-classical picture of electrons. Here, via a comprehensive single-crystal neutron diffraction and first-principles density functional theory study of the archetypical topological kagome metal Mn$_3$Sn, which is also a magnetic Weyl fermion material and a promising chiral magnet for antiferromagnetic spintronics, we report the realisation of an emergent spin-density wave (SDW) order, a hallmark correlated many-body phenomenon, that is engineered by the Fermi surface nesting of topological flat bands. We further reveal that the phase transition, from the well-known high-temperature coplanar and non-collinear k = 0 inverse triangular antiferromagnetic order to a double-$k$ non-coplanar modulated incommensurate magnetic structure below $T_1$ = 280 K, is primarily driven by the SDW instability. The double-$k$ nature of this complex low-temperature magnetic order, which can be regarded as an intriguing superposition of a longitudinal SDW with a modulation wavevector k$_L$ and a transverse incommensurate helical magnetic order with a modulation wavevector k$_T$, is unambiguously confirmed by our observation of the inter-modulation high-order harmonics of the type of 2k$_L$+k$_T$. This discovery not only solves a long-standing puzzle concerning the nature of the phase transition at $T_1$, but also provides an extraordinary example on the intrinsic engineering of correlated many-body phenomena in topological matter. The identified multi-$k$ magnetic state can be further exploited for the engineering of the new modes of magnetization and chirality switching in antiferromagnetic spintronics.

cond-mat.str-el↗
arXiv2023

Integrated Photonic Encoder for Terapixel Image Processing

Modern lens designs are capable of resolving >10 gigapixels, while advances in camera frame-rate and hyperspectral imaging have made Terapixel/s data acquisition a real possibility. The main bottlenecks preventing such high data-rate systems are power consumption and data storage. In this work, we show that analog photonic encoders could address this challenge, enabling high-speed image compression using orders-of-magnitude lower power than digital electronics. Our approach relies on a silicon-photonics front-end to compress raw image data, foregoing energy-intensive image conditioning and reducing data storage requirements. The compression scheme uses a passive disordered photonic structure to perform kernel-type random projections of the raw image data with minimal power consumption and low latency. A back-end neural network can then reconstruct the original images with structural similarity exceeding 90%. This scheme has the potential to process Terapixel/s data streams using less than 100 fJ/pixel, providing a path to ultra-high-resolution data and image acquisition systems.

physics.optics↗
arXiv2023

Exploiting Scratchpad Memory for Deep Temporal Blocking: A case study for 2D Jacobian 5-point iterative stencil kernel (j2d5pt)

General Purpose Graphics Processing Units (GPGPU) are used in most of the top systems in HPC. The total capacity of scratchpad memory has increased by more than 40 times in the last decade. However, existing optimizations for stencil computations using temporal blocking have not aggressively exploited the large capacity of scratchpad memory. This work uses the 2D Jacobian 5-point iterative stencil as a case study to investigate the use of large scratchpad memory. Unlike existing research that tiles the domain in a thread block fashion, we tile the domain so that each tile is large enough to utilize all available scratchpad memory on the GPU. Consequently, we process several time steps inside a single tile before offloading the result back to global memory. Our evaluation shows that our performance is comparable to state-of-the-art implementations, yet our implementation is much simpler and does not require auto-generation of code.

cs.DC↗
arXiv2023

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this approach to the joint modeling of language and vision. PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages. To train PaLI, we make use of large pre-trained encoder-decoder language models and Vision Transformers (ViTs). This allows us to capitalize on their existing capabilities and leverage the substantial cost of training them. We find that joint scaling of the vision and language components is important. Since existing Transformers for language are much larger than their vision counterparts, we train a large, 4-billion parameter ViT (ViT-e) to quantify the benefits from even larger-capacity vision models. To train PaLI, we create a large multilingual mix of pretraining tasks, based on a new image-text training set containing 10B images and texts in over 100 languages. PaLI achieves state-of-the-art in multiple vision and language tasks (such as captioning, visual question-answering, scene-text understanding), while retaining a simple, modular, and scalable design.

cs.CV↗
arXiv2023

AMatFormer: Efficient Feature Matching via Anchor Matching Transformer

Learning based feature matching methods have been commonly studied in recent years. The core issue for learning feature matching is to how to learn (1) discriminative representations for feature points (or regions) within each intra-image and (2) consensus representations for feature points across inter-images. Recently, self- and cross-attention models have been exploited to address this issue. However, in many scenes, features are coming with large-scale, redundant and outliers contaminated. Previous self-/cross-attention models generally conduct message passing on all primal features which thus lead to redundant learning and high computational cost. To mitigate limitations, inspired by recent seed matching methods, in this paper, we propose a novel efficient Anchor Matching Transformer (AMatFormer) for the feature matching problem. AMatFormer has two main aspects: First, it mainly conducts self-/cross-attention on some anchor features and leverages these anchor features as message bottleneck to learn the representations for all primal features. Thus, it can be implemented efficiently and compactly. Second, AMatFormer adopts a shared FFN module to further embed the features of two images into the common domain and thus learn the consensus feature representations for the matching problem. Experiments on several benchmarks demonstrate the effectiveness and efficiency of the proposed AMatFormer matching approach.

cs.CV↗
arXiv2023

PaLI-X: On Scaling up a Multilingual Vision and Language Model

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

cs.CV↗
arXiv2023

Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model

Pretrained language models have achieved remarkable success in various natural language processing tasks. However, pretraining has recently shifted toward larger models and larger data, and this has resulted in significant computational and energy costs. In this paper, we propose Influence Subset Selection (ISS) for language model, which explicitly utilizes end-task knowledge to select a tiny subset of the pretraining corpus. Specifically, the ISS selects the samples that will provide the most positive influence on the performance of the end-task. Furthermore, we design a gradient matching based influence estimation method, which can drastically reduce the computation time of influence. With only 0.45% of the data and a three-orders-of-magnitude lower computational cost, ISS outperformed pretrained models (e.g., RoBERTa) on eight datasets covering four domains.

cs.CL↗
arXiv2023

PERKS: a Locality-Optimized Execution Model for Iterative Memory-bound GPU Applications

Iterative memory-bound solvers commonly occur in HPC codes. Typical GPU implementations have a loop on the host side that invokes the GPU kernel as much as time/algorithm steps there are. The termination of each kernel implicitly acts the barrier required after advancing the solution every time step. We propose an execution model for running memory-bound iterative GPU kernels: PERsistent KernelS (PERKS). In this model, the time loop is moved inside persistent kernel, and device-wide barriers are used for synchronization. We then reduce the traffic to device memory by caching subset of the output in each time step in the unused registers and shared memory. PERKS can be generalized to any iterative solver: they largely independent of the solver's implementation. We explain the design principle of PERKS and demonstrate effectiveness of PERKS for a wide range of iterative 2D/3D stencil benchmarks (geomean speedup of $2.12$x for 2D stencils and $1.24$x for 3D stencils over state-of-art libraries), and a Krylov subspace conjugate gradient solver (geomean speedup of $4.86$x in smaller SpMV datasets from SuiteSparse and $1.43$x in larger SpMV datasets over a state-of-art library). All PERKS-based implementations available at: https://github.com/neozhang307/PERKS.

cs.DC↗
arXiv2023

Revisiting Temporal Blocking Stencil Optimizations

Iterative stencils are used widely across the spectrum of High Performance Computing (HPC) applications. Many efforts have been put into optimizing stencil GPU kernels, given the prevalence of GPU-accelerated supercomputers. To improve the data locality, temporal blocking is an optimization that combines a batch of time steps to process them together. Under the observation that GPUs are evolving to resemble CPUs in some aspects, we revisit temporal blocking optimizations for GPUs. We explore how temporal blocking schemes can be adapted to the new features in the recent Nvidia GPUs, including large scratchpad memory, hardware prefetching, and device-wide synchronization. We propose a novel temporal blocking method, EBISU, which champions low device occupancy to drive aggressive deep temporal blocking on large tiles that are executed tile-by-tile. We compare EBISU with state-of-the-art temporal blocking libraries: STENCILGEN and AN5D. We also compare with state-of-the-art stencil auto-tuning tools that are equipped with temporal blocking optimizations: ARTEMIS and DRSTENCIL. Over a wide range of stencil benchmarks, EBISU achieves speedups up to $2.53$x and a geometric mean speedup of $1.49$x over the best state-of-the-art performance in each stencil benchmark.

cs.DC↗
arXiv2023

ReGeneration Learning of Diffusion Models with Rich Prompts for Zero-Shot Image Translation

Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and contextually relevant descriptions for the desired image modifications. Secondly, current models can impose significant changes to the original image content during the editing process. In this paper, we explore ReGeneration learning in an image-to-image Diffusion model (ReDiffuser), that preserves the content of the original image without human prompting and the requisite editing direction is automatically discovered within the text embedding space. To ensure consistent preservation of the shape during image editing, we propose cross-attention guidance based on regeneration learning. This novel approach allows for enhanced expression of the target domain features while preserving the original shape of the image. In addition, we introduce a cooperative update strategy, which allows for efficient preservation of the original shape of an image, thereby improving the quality and consistency of shape preservation throughout the editing process. Our proposed method leverages an existing pre-trained text-image diffusion model without any additional training. Extensive experiments show that the proposed method outperforms existing work in both real and synthetic image editing.

cs.CV↗
arXiv2023

Spin-phonon scattering-induced low thermal conductivity in a van der Waals layered ferromagnet Cr$_2$Si$_2$Te$_6$

Layered van der Waals (vdW) magnets are prominent playgrounds for developing magnetoelectric, magneto-optic and spintronic devices. In spintronics, particularly in spincaloritronic applications, low thermal conductivity ($κ$) is highly desired. Here, by combining thermal transport measurements with density functional theory calculations, we demonstrate low $κ$ down to 1 W m$^{-1}$ K$^{-1}$ in a typical vdW ferromagnet Cr$_2$Si$_2$Te$_6$. In the paramagnetic state, development of magnetic fluctuations way above $T_\mathrm{c}=$ 33 K strongly reduces $κ$ via spin-phonon scattering, leading to low $κ\sim$ 1 W m$^{-1}$ K$^{-1}$ over a wide temperature range, in comparable to that of amorphous silica. In the magnetically ordered state, emergence of resonant magnon-phonon scattering limits $κ$ below $\sim$ 2 W m$^{-1}$ K$^{-1}$, which would be three times larger if magnetic scatterings were absent. Application of magnetic fields strongly suppresses the spin-phonon scattering, giving rise to large enhancements of $κ$. Our calculations well capture these complex behaviours of $κ$ by taking the temperature- and magnetic-field-dependent spin-phonon scattering into account. Realization of low $κ$ which is easily tunable by magnetic fields in Cr$_2$Si$_2$Te$_6$, may further promote spincaloritronic applications of vdW magnets. Our theoretical approach may also provide a generic understanding of spin-phonon scattering, which appears to play important roles in various systems.

cond-mat.mtrl-sci↗
arXiv2023

Single-shot spatial instability and electric control of polariton condensates at room temperature

In planar microcavities, the transverse-electric and transverse-magnetic (TE-TM) mode splitting of cavity photons arises due to their different penetration into the Bragg mirrors and can result in optical spin-orbit coupling (SOC). In this work, we find that in a liquid crystal (LC) microcavity filled with perovskite microplates, the pronounced TE-TM splitting gives rise to a strong SOC that leads to the spatial instability of microcavity polariton condensates under single-shot excitation. Spatially varying hole burning and mode competition occurs between polarization components leading to different condensate profiles from shot to shot. The single-shot polariton condensates become stable when the SOC vanishes as the TE and TM modes are spectrally well separated from each other, which can be achieved by application of an electric field to our LC microcavity with electrically tunable anisotropy. Our findings are well reproduced and traced back to their physical origin by our detailed numerical simulations. With the electrical manipulation our work reveals how the shot-to-shot spatial instability of spatial polariton profiles can be engineered in anisotropic microcavities at room temperature, which will benefit the development of stable polariton-based optoeletronic and light-emitting devices.

physics.optics↗