arXiv subjects

Wei Jin

Publications and source records attributed to Wei Jin.

At least 109 records · Page 6Linked to original sources

arXiv2021

Elastic Graph Neural Networks

While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on $\ell_1$ and $\ell_2$-based graph smoothing. In particular, we propose a novel and general message passing scheme into GNNs. This message passing algorithm is not only friendly to back-propagation training but also achieves the desired smoothing properties with a theoretical convergence guarantee. Experiments on semi-supervised learning tasks demonstrate that the proposed Elastic GNNs obtain better adaptivity on benchmark datasets and are significantly robust to graph adversarial attacks. The implementation of Elastic GNNs is available at \url{https://github.com/lxiaorui/ElasticGNN}.

cs.LG↗

arXiv2021

Vertex quasiprimitive two-geodesic transitive graphs

For a non-complete graph $Γ$, a vertex triple $(u,v,w)$ with $v$ adjacent to both $u$ and $w$ is called a $2$-geodesic if $u\neq w$ and $u,w$ are not adjacent. Then $Γ$ is said to be $2$-geodesic transitive if its automorphism group is transitive on both arcs and 2-geodesics. In previous work the author showed that if a $2$-geodesic transitive graph $Γ$ is locally disconnected and its automorphism group $\Aut(Γ)$ has a non-trivial normal subgroup which is intransitive on the vertex set of $Γ$, then $Γ$ is a cover of a smaller 2-geodesic transitive graph. Thus the `basic' graphs to study are those for which $\Aut(Γ)$ acts quasiprimitively on the vertex set. In this paper, we study 2-geodesic transitive graphs which are locally disconnected and $\Aut(Γ)$ acts quasiprimitively on the vertex set. We first determine all the possible quasiprimitive action types and give examples for them, and then classify the family of $2$-geodesic transitive graphs whose automorphism group is primitive on its vertex set of $\PA$ type.

math.CO↗

arXiv2021

Graph Feature Gating Networks

Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs. Most GNNs follow a message-passing scheme where the node representations are updated by aggregating and transforming the information from the neighborhood. Meanwhile, they adopt the same strategy in aggregating the information from different feature dimensions. However, suggested by social dimension theory and spectral embedding, there are potential benefits to treat the dimensions differently during the aggregation process. In this work, we investigate to enable heterogeneous contributions of feature dimensions in GNNs. In particular, we propose a general graph feature gating network (GFGN) based on the graph signal denoising problem and then correspondingly introduce three graph filters under GFGN to allow different levels of contributions from feature dimensions. Extensive experiments on various real-world datasets demonstrate the effectiveness and robustness of the proposed frameworks.

cs.LG↗

arXiv2021

The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification

It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of bias as explicit bias, which has been extensively studied. However, deep text classification models can also produce biased outcomes for texts written by authors of certain demographic groups. We refer to such bias as implicit bias of which we still have a rather limited understanding. In this paper, we first demonstrate that implicit bias exists in different text classification tasks for different demographic groups. Then, we build a learning-based interpretation method to deepen our knowledge of implicit bias. Specifically, we verify that classifiers learn to make predictions based on language features that are related to the demographic attributes of the authors. Next, we propose a framework Debiased-TC to train deep text classifiers to make predictions on the right features and consequently mitigate implicit bias. We conduct extensive experiments on three real-world datasets. The results show that the text classification models trained under our proposed framework outperform traditional models significantly in terms of fairness, and also slightly in terms of classification performance.

cs.CL↗

arXiv2021

Improvement of Normal Estimation for PointClouds via Simplifying Surface Fitting

With the burst development of neural networks in recent years, the task of normal estimation has once again become a concern. By introducing the neural networks to classic methods based on problem-specific knowledge, the adaptability of the normal estimation algorithm to noise and scale has been greatly improved. However, the compatibility between neural networks and the traditional methods has not been considered. Similar to the principle of Occam's razor, that is, the simpler is better. We observe that a more simplified process of surface fitting can significantly improve the accuracy of the normal estimation. In this paper, two simple-yet-effective strategies are proposed to address the compatibility between the neural networks and surface fitting process to improve normal estimation. Firstly, a dynamic top-k selection strategy is introduced to better focus on the most critical points of a given patch, and the points selected by our learning method tend to fit a surface by way of a simple tangent plane, which can dramatically improve the normal estimation results of patches with sharp corners or complex patterns. Then, we propose a point update strategy before local surface fitting, which smooths the sharp boundary of the patch to simplify the surface fitting process, significantly reducing the fitting distortion and improving the accuracy of the predicted point normal. The experiments analyze the effectiveness of our proposed strategies and demonstrate that our method achieves SOTA results with the advantage of higher estimation accuracy over most existed approaches.

cs.CV↗

arXiv2021

Fast and Accurate Normal Estimation for Point Cloud via Patch Stitching

This paper presents an effective normal estimation method adopting multi-patch stitching for an unstructured point cloud. The majority of learning-based approaches encode a local patch around each point of a whole model and estimate the normals in a point-by-point manner. In contrast, we suggest a more efficient pipeline, in which we introduce a patch-level normal estimation architecture to process a series of overlapping patches. Additionally, a multi-normal selection method based on weights, dubbed as multi-patch stitching, integrates the normals from the overlapping patches. To reduce the adverse effects of sharp corners or noise in a patch, we introduce an adaptive local feature aggregation layer to focus on an anisotropic neighborhood. We then utilize a multi-branch planar experts module to break the mutual influence between underlying piecewise surfaces in a patch. At the stitching stage, we use the learned weights of multi-branch planar experts and distance weights between points to select the best normal from the overlapping parts. Furthermore, we put forward constructing a sparse matrix representation to reduce large-scale retrieval overheads for the loop iterations dramatically. Extensive experiments demonstrate that our method achieves SOTA results with the advantage of lower computational costs and higher robustness to noise over most of the existing approaches.

cs.CV↗

arXiv2021

Node Similarity Preserving Graph Convolutional Networks

Graph Neural Networks (GNNs) have achieved tremendous success in various real-world applications due to their strong ability in graph representation learning. GNNs explore the graph structure and node features by aggregating and transforming information within node neighborhoods. However, through theoretical and empirical analysis, we reveal that the aggregation process of GNNs tends to destroy node similarity in the original feature space. There are many scenarios where node similarity plays a crucial role. Thus, it has motivated the proposed framework SimP-GCN that can effectively and efficiently preserve node similarity while exploiting graph structure. Specifically, to balance information from graph structure and node features, we propose a feature similarity preserving aggregation which adaptively integrates graph structure and node features. Furthermore, we employ self-supervised learning to explicitly capture the complex feature similarity and dissimilarity relations between nodes. We validate the effectiveness of SimP-GCN on seven benchmark datasets including three assortative and four disassorative graphs. The results demonstrate that SimP-GCN outperforms representative baselines. Further probe shows various advantages of the proposed framework. The implementation of SimP-GCN is available at \url{https://github.com/ChandlerBang/SimP-GCN}.

cs.LG↗

arXiv2020

Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability. Adversary can mislead GNNs to give wrong predictions by modifying the graph structure such as manipulating a few edges. This vulnerability has arisen tremendous concerns for adapting GNNs in safety-critical applications and has attracted increasing research attention in recent years. Thus, it is necessary and timely to provide a comprehensive overview of existing graph adversarial attacks and the countermeasures. In this survey, we categorize existing attacks and defenses, and review the corresponding state-of-the-art methods. Furthermore, we have developed a repository with representative algorithms (https://github.com/DSE-MSU/DeepRobust/tree/master/deeprobust/graph). The repository enables us to conduct empirical studies to deepen our understandings on attacks and defenses on graphs.

cs.LG↗

arXiv2020

Graph Structure Learning for Robust Graph Neural Networks

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in making predictions for downstream tasks. The vulnerability to adversarial attacks has raised increasing concerns for applying GNNs in safety-critical applications. Therefore, developing robust algorithms to defend adversarial attacks is of great significance. A natural idea to defend adversarial attacks is to clean the perturbed graph. It is evident that real-world graphs share some intrinsic properties. For example, many real-world graphs are low-rank and sparse, and the features of two adjacent nodes tend to be similar. In fact, we find that adversarial attacks are likely to violate these graph properties. Therefore, in this paper, we explore these properties to defend adversarial attacks on graphs. In particular, we propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model from the perturbed graph guided by these properties. Extensive experiments on real-world graphs demonstrate that the proposed framework achieves significantly better performance compared with the state-of-the-art defense methods, even when the graph is heavily perturbed. We release the implementation of Pro-GNN to our DeepRobust repository for adversarial attacks and defenses (footnote: https://github.com/DSE-MSU/DeepRobust). The specific experimental settings to reproduce our results can be found in https://github.com/ChandlerBang/Pro-GNN.

cs.LG↗

arXiv2020

Self-supervised Learning on Graphs: Deep Insights and New Direction

The success of deep learning notoriously requires larger amounts of costly annotated data. This has led to the development of self-supervised learning (SSL) that aims to alleviate this limitation by creating domain specific pretext tasks on unlabeled data. Simultaneously, there are increasing interests in generalizing deep learning to the graph domain in the form of graph neural networks (GNNs). GNNs can naturally utilize unlabeled nodes through the simple neighborhood aggregation that is unable to thoroughly make use of unlabeled nodes. Thus, we seek to harness SSL for GNNs to fully exploit the unlabeled data. Different from data instances in the image and text domains, nodes in graphs present unique structure information and they are inherently linked indicating not independent and identically distributed (or i.i.d.). Such complexity is a double-edged sword for SSL on graphs. On the one hand, it determines that it is challenging to adopt solutions from the image and text domains to graphs and dedicated efforts are desired. On the other hand, it provides rich information that enables us to build SSL from a variety of perspectives. Thus, in this paper, we first deepen our understandings on when, why, and which strategies of SSL work with GNNs by empirically studying numerous basic SSL pretext tasks on graphs. Inspired by deep insights from the empirical studies, we propose a new direction SelfTask to build advanced pretext tasks that are able to achieve state-of-the-art performance on various real-world datasets. The specific experimental settings to reproduce our results can be found in \url{https://github.com/ChandlerBang/SelfTask-GNN}.

cs.LG↗

arXiv2020

DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses

DeepRobust is a PyTorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. It currently contains more than 10 attack algorithms and 8 defense algorithms in image domain and 9 attack algorithms and 4 defense algorithms in graph domain, under a variety of deep learning architectures. In this manual, we introduce the main contents of DeepRobust with detailed instructions. The library is kept updated and can be found at https://github.com/DSE-MSU/DeepRobust.

cs.LG↗

arXiv2020

A Bayesian Nonparametric Approach for Inferring Drug Combination Effects on Mental Health in People with HIV

Although combination antiretroviral therapy (ART) is highly effective in suppressing viral load for people with HIV (PWH), many ART agents may exacerbate central nervous system (CNS)-related adverse effects including depression. Therefore, understanding the effects of ART drugs on the CNS function, especially mental health, can help clinicians personalize medicine with less adverse effects for PWH and prevent them from discontinuing their ART to avoid undesirable health outcomes and increased likelihood of HIV transmission. The emergence of electronic health records offers researchers unprecedented access to HIV data including individuals' mental health records, drug prescriptions, and clinical information over time. However, modeling such data is very challenging due to high-dimensionality of the drug combination space, the individual heterogeneity, and sparseness of the observed drug combinations. We develop a Bayesian nonparametric approach to learn drug combination effect on mental health in PWH adjusting for socio-demographic, behavioral, and clinical factors. The proposed method is built upon the subset-tree kernel method that represents drug combinations in a way that synthesizes known regimen structure into a single mathematical representation. It also utilizes a distance-dependent Chinese restaurant process to cluster heterogeneous population while taking into account individuals' treatment histories. We evaluate the proposed approach through simulation studies, and apply the method to a dataset from the Women's Interagency HIV Study, yielding interpretable and promising results. Our method has clinical utility in guiding clinicians to prescribe more informed and effective personalized treatment based on individuals' treatment histories and clinical characteristics.

stat.ME↗

arXiv2019

A Theoretical Framework for Bayesian Nonparametric Regression

We develop a unifying framework for Bayesian nonparametric regression to study the rates of contraction with respect to the integrated $L_2$-distance without assuming the regression function space to be uniformly bounded. The framework is very flexible and can be applied to a wide class of nonparametric prior models. Three non-trivial applications of the proposed framework are provided: The finite random series regression of an $α$-Hölder function, with adaptive rates of contraction up to a logarithmic factor; The un-modified block prior regression of an $α$-Sobolev function, with adaptive-and-exact rates of contraction; The Gaussian spline regression of an $α$-Hölder function, with the near-optimal posterior contraction. These applications serve as generalization or complement of their respective results in the literature. Extensions to the fixed-design regression problem and sparse additive models in high dimensions are discussed as well.

math.ST↗

arXiv2019

Finite 2-arc-transitive strongly regular graphs and 3-geodesic-transitive graphs

We classify all the $2$-arc-transitive strongly regular graphs, and use this classification to study the family of finite $(G,3)$-geodesic-transitive graphs of girth $4$ or $5$ for some group $G$ of automorphisms. For this application we first give a reduction result on the latter family of graphs: let $N$ be a normal subgroup of $G$ which has at least $3$ orbits on vertices. We show that $Γ$ is a cover of its quotient $Γ_N$ modulo the $N$-orbits, and that either $Γ_N$ is $(G/N,3)$-geodesic-transitive of the same girth as $Γ$, or $Γ_N$ is a $(G/N,2)$-arc-transitive strongly regular graph, or $Γ_N$ is a complete graph with $G/N$ acting 3-transitively on vertices. The classification of $2$-arc-transitive strongly regular graphs allows us to characterise the $(G,3)$-geodesic-transitive covers $Γ$ when $Γ_N$ is complete or strongly regular.

math.CO↗

arXiv2018

Learning Feature Representations for Keyphrase Extraction

In supervised approaches for keyphrase extraction, a candidate phrase is encoded with a set of hand-crafted features and machine learning algorithms are trained to discriminate keyphrases from non-keyphrases. Although the manually-designed features have shown to work well in practice, feature engineering is a difficult process that requires expert knowledge and normally does not generalize well. In this paper, we present SurfKE, a feature learning framework that exploits the text itself to automatically discover patterns that keyphrases exhibit. Our model represents the document as a graph and automatically learns feature representation of phrases. The proposed model obtains remarkable improvements in performance over strong baselines.

cs.CL↗

arXiv2017

Model of ultrafast demagnetization driven by spin-orbit coupling in a photoexcited antiferromagnetic insulator Cr2O3

We theoretically study the dynamic time evolution following laser pulse pumping in an antiferromagnetic insulator Cr$_{2}$O$_{3}$. From the photoexcited high-spin quartet states to the long-lived low-spin doublet states, the ultrafast demagnetization processes are investigated by solving the dissipative Schrödinger equation. We find that the demagnetization times are of the order of hundreds of femtosecond, in good agreement with recent experiments. The switching times could be strongly reduced by properly tuning the energy gaps between the multiplet energy levels of Cr$^{3+}$. Furthermore, the relaxation times also depend on the hybridization of atomic orbitals in the first photoexcited state. Our results suggest that the selective manipulation of electronic structure by engineering stress-strain or chemical substitution allows effective control of the magnetic state switching in photoexcited insulating transition-metal oxides.

cond-mat.str-el↗

arXiv2017

Bernoulli's type Law of Euler Equations on Sobolev Space in $\mathbb{R}^{3}$

In this paper, we discuss Bernoulli's principle to the 3-dimensional incompressible Euler equation in a bounded local Lipschitz domain $Ω\subset\mathbb{R}^{3}$ with a Lipschitz boundary. Using topological properties of the level set and Morse-Sard theorem, we will prove Bernoulli's principle on Sobolev space.

math.AP↗

arXiv2016

All-fiber hydrogen sensor based on stimulated Raman gain spectroscopy with a 1550 nm hollow-core fiber

We report a highly sensitive all-fiber hydrogen sensor based on continuous-wave stimulated Raman gain spectroscopy with a hollow-core photonic crystal fiber operating around 1550 nm. A pump-probe configuration is used, in which the frequency difference between the pump and the probe lasers is tuned to the S0(0) transition of para-hydrogen with a Raman shift of 354 cm-1. Preliminary experiments demonstrate a detection limit down to 17 ppm with a 250 s averaging time, and further improvement is possible. The all-fiber configuration operating in the telecommunication wavelength band would enable cost-effective and compact sensors for high sensitivity and high-resolution trace analysis.

physics.ins-det↗