arXiv subjects

Lu Zhang

Publications and source records attributed to Lu Zhang.

At least 343 records · Page 19Linked to original sources

arXiv2022

Generalized Equivariance and Preferential Labeling for GNN Node Classification

Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content. However, graphs with unattributed nodes widely exist in real-world applications (e.g., anonymized social networks). Previous GNNs either assign random labels to nodes (which introduces artefacts to the GNN) or assign one embedding to all nodes (which fails to explicitly distinguish one node from another). Further, when these GNNs are applied to unattributed node classification problems, they have an undesired equivariance property, which are fundamentally unable to address the data with multiple possible outputs. In this paper, we analyze the limitation of existing approaches to node classification problems. Inspired by our analysis, we propose a generalized equivariance property and a Preferential Labeling technique that satisfies the desired property asymptotically. Experimental results show that we achieve high performance in several unattributed node classification tasks.

cs.LG↗

arXiv2022

On the hyper-singular boundary integral equation methods for dynamic poroelasticity: three dimensional case

In our previous work [SIAM J. Sci. Comput. 43(3) (2021) B784-B810], an accurate hyper-singular boundary integral equation method for dynamic poroelasticity in two dimensions has been developed. This work is devoted to studying the more complex and difficult three-dimensional problems with Neumann boundary condition and both the direct and indirect methods are adopted to construct combined boundary integral equations. The strongly-singular and hyper-singular integral operators are reformulated into compositions of weakly-singular integral operators and tangential-derivative operators, which allow us to prove the jump relations associated with the poroelastic layer potentials and boundary integral operators in a simple manner. Relying on both the investigated spectral properties of the strongly-singular operators, which indicate that the corresponding eigenvalues accumulate at three points whose values are only dependent on two Lamé constants, and the spectral properties of the Calderón relations of the poroelasticity, we propose low-GMRES-iteration regularized integral equations. Numerical examples are presented to demonstrate the accuracy and efficiency of the proposed methodology by means of a Chebyshev-based rectangular-polar solver.

math.NA↗

arXiv2022

Stability analysis of the Tsallis holographic dark energy model

Using the generalized Tsallis entropy, the Tsallis holographic dark energy(THDE) was proposed recently. In this paper we analyze the cosmological consequences of the THDE model with an interaction between dark energy and dark matter $Q=H(αρ_{m}+βρ_{D})$. We find that the THDE model can explain the current accelerated cosmic expansion, and it is stable under certain conditions. Furthermore, through investigating the dynamical analysis, we find that there exists an attractor which represents an accelerated expansion phase of the universe. When $β=0$, this attractor corresponds to a dark energy dominated de Sitter solution and the universe can evolve into an era which is depicted by the $Λ$CDM model. The age of universe in this model is also explored.

gr-qc↗

arXiv2022

DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations

AI-aided drug discovery (AIDD) is gaining increasing popularity due to its promise of making the search for new pharmaceuticals quicker, cheaper and more efficient. In spite of its extensive use in many fields, such as ADMET prediction, virtual screening, protein folding and generative chemistry, little has been explored in terms of the out-of-distribution (OOD) learning problem with \emph{noise}, which is inevitable in real world AIDD applications. In this work, we present DrugOOD, a systematic OOD dataset curator and benchmark for AI-aided drug discovery, which comes with an open-source Python package that fully automates the data curation and OOD benchmarking processes. We focus on one of the most crucial problems in AIDD: drug target binding affinity prediction, which involves both macromolecule (protein target) and small-molecule (drug compound). In contrast to only providing fixed datasets, DrugOOD offers automated dataset curator with user-friendly customization scripts, rich domain annotations aligned with biochemistry knowledge, realistic noise annotations and rigorous benchmarking of state-of-the-art OOD algorithms. Since the molecular data is often modeled as irregular graphs using graph neural network (GNN) backbones, DrugOOD also serves as a valuable testbed for \emph{graph OOD learning} problems. Extensive empirical studies have shown a significant performance gap between in-distribution and out-of-distribution experiments, which highlights the need to develop better schemes that can allow for OOD generalization under noise for AIDD.

cs.LG↗

arXiv2022

A high order finite difference method for the elastic wave equation in bounded domains with nonconforming interfaces

We develop a stable finite difference method for the elastic wave equation in bounded media, where the material properties can be discontinuous at curved interfaces. The governing equation is discretized in second order form by a fourth or sixth order accurate summation-by-parts operator. The mesh size is determined by the velocity structure of the material, resulting in nonconforming grid interfaces with hanging nodes. We use order-preserving interpolation and the ghost point technique to couple adjacent mesh blocks in an energy-conserving manner, which is supported by a fully discrete stability analysis. In our previous work for the wave equation, two pairs of order-preserving interpolation operators are needed when imposing the interface conditions weakly by a penalty technique. Here, we only use one pair in the ghost point method. In numerical experiments, we demonstrate that the convergence rate is optimal, and is the same as when a globally uniform mesh is used in a single domain. In addition, with a predictor-corrector time integration method, we obtain time stepping stability with stepsize almost the same as given by the usual Courant-Friedrichs-Lewy condition.

math.NA↗

arXiv2021

Adaptively Sketched Bregman Projection Methods for Linear Systems

The sketch-and-project, as a general archetypal algorithm for solving linear systems, unifies a variety of randomized iterative methods such as the randomized Kaczmarz and randomized coordinate descent. However, since it aims to find a least-norm solution from a linear system, the randomized sparse Kaczmarz can not be included. This motivates us to propose a more general framework, called sketched Bregman projection (SBP) method, in which we are able to find solutions with certain structures from linear systems. To generalize the concept of adaptive sampling to the SBP method, we show how the progress, measured by Bregman distance, of single step depends directly on a sketched loss function. Theoretically, we provide detailed global convergence results for the SBP method with different adaptive sampling rules. At last, for the (sparse) Kaczmarz methods, a group of numerical simulations are tested, with which we verify that the methods utilizing sampling Kaczmarz-Motzkin rule demands the fewest computational costs to achieve a given error bound comparing to the corresponding methods with other sampling rules.

math.NA↗

arXiv2021

SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos

Salient human detection (SHD) in dynamic 360° immersive videos is of great importance for various applications such as robotics, inter-human and human-object interaction in augmented reality. However, 360° video SHD has been seldom discussed in the computer vision community due to a lack of datasets with large-scale omnidirectional videos and rich annotations. To this end, we propose SHD360, the first 360° video SHD dataset which contains various real-life daily scenes. Since so far there is no method proposed for 360° image/video SHD, we systematically benchmark 11 representative state-of-the-art salient object detection (SOD) approaches on our SHD360, and explore key issues derived from extensive experimenting results. We hope our proposed dataset and benchmark could serve as a good starting point for advancing human-centric researches towards 360° panoramic data. The dataset is available at https://github.com/PanoAsh/SHD360.

cs.CV↗

arXiv2021

Reducing current crowding in meander superconducting strip single-photon detectors by thickening bends

To facilitate high optical coupling efficiency and absorptance, the active area of a superconducting nano/microstrip single-photon detector (SNSPD/SMSPD) is often designed as a meander configuration with a high filling factor (e.g., >=0.5). However, the switching current (Isw) of SNSPD/SMSPD, at which the detector switches into the normal state, is significantly suppressed by a geometry-induced "current crowding effect", where there are sharp bends in the strip. Here we propose and experimentally verify an alternative method to reduce current crowding both in SNSPD and SMSPD by directly increasing the thickness of the bends through the deposition and lift-off of a secondary superconducting film. We measure and compare the performance of SNSPDs and SMSPDs with different filling factors and bend configurations, with or without thickened bends. Improvements for detectors were observed in detection efficiency, intrinsic dark count rate, and time jitter, owing to the enhanced Isw. Our method provides a promising way of optimizing SNSPD/SMSPD detection performance.

physics.app-ph↗

arXiv2021

Experimental verification of phase discontinuities induced scintillation enhancement under weak perturbations

We verify the existence of scintillation enhancement by measuring the scintillation index of a beam composed of two coherent Gaussian vortex beams with $\pm 1$ topological charges propagating through thermally induced turbulence. Further experimental research based on the reference wave interferometric method demonstrates that this phenomenon is caused by the combined effect of a screw dislocation and an infinitely extended edge dislocation, namely the impact of an anisotropic dislocation. The experimental results indicate that the anisotropic dislocation is more sensitive to weak perturbations than an isotropic screw dislocation and an infinitely extended edge dislocation, which means the anisotropic dislocation has potential for weak perturbation measurement. This phenomenon is instructive in further phase discontinuity research.

physics.optics↗

arXiv2021

CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection

In the past few years, numerous deep learning methods have been proposed to address the task of segmenting salient objects from RGB images. However, these approaches depending on single modality fail to achieve the state-of-the-art performance on widely used light field salient object detection (SOD) datasets, which collect large-scale natural images and provide multiple modalities such as multi-view, micro-lens images and depth maps. Most recently proposed light field SOD methods have acquired improving detecting accuracy, yet still predict rough objects' structures and perform slow inference speed. To this end, we propose CMA-Net, which consists of two novel cascaded mutual attention modules aiming at fusing the high level features from the modalities of all-in-focus and depth. Our proposed CMA-Net outperforms 30 SOD methods on two widely applied light field benchmark datasets. Besides, the proposed CMA-Net is able to inference at the speed of 53 fps. Extensive quantitative and qualitative experiments illustrate both the effectiveness and efficiency of our CMA-Net.

cs.CV↗

arXiv2021

Transformer-based Network for RGB-D Saliency Detection

RGB-D saliency detection integrates information from both RGB images and depth maps to improve prediction of salient regions under challenging conditions. The key to RGB-D saliency detection is to fully mine and fuse information at multiple scales across the two modalities. Previous approaches tend to apply the multi-scale and multi-modal fusion separately via local operations, which fails to capture long-range dependencies. Here we propose a transformer-based network to address this issue. Our proposed architecture is composed of two modules: a transformer-based within-modality feature enhancement module (TWFEM) and a transformer-based feature fusion module (TFFM). TFFM conducts a sufficient feature fusion by integrating features from multiple scales and two modalities over all positions simultaneously. TWFEM enhances feature on each scale by selecting and integrating complementary information from other scales within the same modality before TFFM. We show that transformer is a uniform operation which presents great efficacy in both feature fusion and feature enhancement, and simplifies the model design. Extensive experimental results on six benchmark datasets demonstrate that our proposed network performs favorably against state-of-the-art RGB-D saliency detection methods.

cs.CV↗

arXiv2021

SAFA: Structure Aware Face Animation

Recent success of generative adversarial networks (GAN) has made great progress on the face animation task. However, the complex scene structure of a face image still makes it a challenge to generate videos with face poses significantly deviating from the source image. On one hand, without knowing the facial geometric structure, generated face images might be improperly distorted. On the other hand, some area of the generated image might be occluded in the source image, which makes it difficult for GAN to generate realistic appearance. To address these problems, we propose a structure aware face animation (SAFA) method which constructs specific geometric structures to model different components of a face image. Following the well recognized motion based face animation technique, we use a 3D morphable model (3DMM) to model the face, multiple affine transforms to model the other foreground components like hair and beard, and an identity transform to model the background. The 3DMM geometric embedding not only helps generate realistic structure for the driving scene, but also contributes to better perception of occluded area in the generated image. Besides, we further propose to exploit the widely studied inpainting technique to faithfully recover the occluded image area. Both quantitative and qualitative experiment results have shown the superiority of our method. Code is available at https://github.com/Qiulin-W/SAFA.

cs.CV↗

arXiv2021

New insights in smoothness and strong convexity with improved convergence of gradient descent

The starting assumptions to study the convergence and complexity of gradient-type methods may be the smoothness (also called Lipschitz continuity of gradient) and the strong convexity. In this note, we revisit these two basic properties from a new perspective that motivates their definitions and equivalent characterizations, along with an improved linear convergence of the gradient descent method.

math.OC↗

arXiv2021

DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples

The scarcity of labeled data is a critical obstacle to deep learning. Semi-supervised learning (SSL) provides a promising way to leverage unlabeled data by pseudo labels. However, when the size of labeled data is very small (say a few labeled samples per class), SSL performs poorly and unstably, possibly due to the low quality of learned pseudo labels. In this paper, we propose a new SSL method called DP-SSL that adopts an innovative data programming (DP) scheme to generate probabilistic labels for unlabeled data. Different from existing DP methods that rely on human experts to provide initial labeling functions (LFs), we develop a multiple-choice learning~(MCL) based approach to automatically generate LFs from scratch in SSL style. With the noisy labels produced by the LFs, we design a label model to resolve the conflict and overlap among the noisy labels, and finally infer probabilistic labels for unlabeled samples. Extensive experiments on four standard SSL benchmarks show that DP-SSL can provide reliable labels for unlabeled data and achieve better classification performance on test sets than existing SSL methods, especially when only a small number of labeled samples are available. Concretely, for CIFAR-10 with only 40 labeled samples, DP-SSL achieves 93.82% annotation accuracy on unlabeled data and 93.46% classification accuracy on test data, which are higher than the SOTA results.

cs.CV↗

arXiv2021

Learning Synergistic Attention for Light Field Salient Object Detection

We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms. Our SA-Net exploits the rich information of focal stacks via 3D convolutional neural networks, decodes the high-level features of multi-modal light field data with two cascaded synergistic attention modules, and predicts the saliency map using an effective feature fusion module in a progressive manner. Extensive experiments on three widely-used benchmark datasets show that our SA-Net outperforms 28 state-of-the-art models, sufficiently demonstrating its effectiveness and superiority. Our code is available at https://github.com/PanoAsh/SA-Net.

cs.CV↗

arXiv2021

Charge instability of topological Fermi arcs in chiral crystal CoSi

Topological boundary states, emerged at the spatial boundary between topological non-trivial and trivial phases, are usually gapless, or commonly referred as metallic states. For example, the surface state of a topological insulator is a gapless Dirac state. These metallic topological boundary states are typically well described by non-interacting fermions. However, the behavior of topological boundary states with significant electron-electron interactions, which could turn the gapless boundary states into gapped ordered states, e.g., density wave states or superconducting states, is of great interest theoretically, but is still lacking evidence experimentally. Here, we report the observation of incommensurable charge density wave (CDW) formed on the topological boundary states driven by the electron-electron interactions on the (001) surface of CoSi. The wavevector of CDW varies as the temperature changes, which coincides with the evolution of topological surface Fermi arcs with temperature. The orientation of CDW phase is determined by the chirality of the Fermi arcs, which indicates direct association between CDW and Fermi arcs. Our finding will stimulate the search of more interactions-driven ordered states, such as superconductivity and magnetism, on the boundaries of topological materials.

cond-mat.str-el↗

arXiv2021

Weakly-supervised Text Classification Based on Keyword Graph

Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to generate pseudo-labels for unlabeled texts. However, existing methods treat keywords independently, thus ignore the correlation among them, which should be useful if properly exploited. In this paper, we propose a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN. Our framework is an iterative process. In each iteration, we first construct a keyword graph, so the task of assigning pseudo labels is transformed to annotating keyword subgraphs. To improve the annotation quality, we introduce a self-supervised task to pretrain a subgraph annotator, and then finetune it. With the pseudo labels generated by the subgraph annotator, we then train a text classifier to classify the unlabeled texts. Finally, we re-extract keywords from the classified texts. Extensive experiments on both long-text and short-text datasets show that our method substantially outperforms the existing ones

cs.CL↗

arXiv2021

Achieving Counterfactual Fairness for Causal Bandit

In online recommendation, customers arrive in a sequential and stochastic manner from an underlying distribution and the online decision model recommends a chosen item for each arriving individual based on some strategy. We study how to recommend an item at each step to maximize the expected reward while achieving user-side fairness for customers, i.e., customers who share similar profiles will receive a similar reward regardless of their sensitive attributes and items being recommended. By incorporating causal inference into bandits and adopting soft intervention to model the arm selection strategy, we first propose the d-separation based UCB algorithm (D-UCB) to explore the utilization of the d-separation set in reducing the amount of exploration needed to achieve low cumulative regret. Based on that, we then propose the fair causal bandit (F-UCB) for achieving the counterfactual individual fairness. Both theoretical analysis and empirical evaluation demonstrate effectiveness of our algorithms.

cs.LG↗