Author name cluster

Zheng Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

TCS Journal 2026 Journal Article

Structure connectivity and substructure connectivity of strong exchanged hypercube

Zheng Ma
Shengzhang Ren

As a fundamental variant of hypercube networks, the exchanged hypercube EH(s, t) is among the most prevalent interconnection topologies in modern computing systems. While connectivity is closely related to network reliability and fault tolerance. The exchange hypercube EH(s, t) is a common interconnection topology. To enhance its connectivity, we propose the strong exchange hypercube (SEH(s, t)) by adding a set of specific edges, denoted as E 4. Lin et al. extended the notion of connectivity by introducing two new kinds of connectivity, called structure connectivity κ(G; H) and substructure connectivity κs (SEH(s, t); H), respectively. In this paper, we characterize the κ(SEH(s, t); H) and κs (SEH(s, t); H) of SEH(s, t) for H ∈ {Pk, K 1, r, C 2m }, where 2 ⩽ k ⩽ 2 s + 1 ⩽ s + t + 1, 2 ≤ r ≤ s ≤ t, 4 ≤ 2m ≤ 2s.

Details DOI

AAAI Conference 2026 Conference Paper

Towards Multiple Missing Values-resistant Unsupervised Graph Anomaly Detection

Jiazhen Chen
Xiuqin Liang
Sichao Fu
Zheng Ma
Weihua Ou

Unsupervised graph anomaly detection (GAD) has received increasing attention in recent years. It aims to identify anomalous data patterns using only unlabeled node information from graph-structured data. However, prevailing unsupervised GAD methods typically assume complete node attributes and structural information-a condition that is seldom satisfied in real-world scenarios due to privacy constraints, collection errors, or dynamic node arrivals. Standard imputation strategies risk "repairing" rare anomalous nodes so that they appear normal, thereby introducing imputation bias into the detection process. Moreover, when both node attributes and edges are missing simultaneously, estimation errors in one view can contaminate the other, causing cross-view interference that further degrades detection performance. To address these challenges, we propose M²V-UGAD, a multiple-missing-values-resistant unsupervised GAD framework for incomplete graphs. Specifically, we introduce a dual-pathway encoder that independently reconstructs missing node attributes and graph structure, preventing errors in one view from propagating to the other. The two pathways are then fused and regularized within a joint latent space such that normal nodes occupy a compact inner manifold while anomalies lie on an outer shell. Finally, to mitigate imputation bias, we sample latent codes just outside the normal region and decode them into realistic node features and subgraphs, yielding hard negative examples that sharpen the decision boundary. Experiments on seven public benchmarks show that M²V-UGAD consistently outperforms existing unsupervised GAD methods across a range of missing rates.

PDF Details DOI

AAAI Conference 2024 Conference Paper

A Hierarchical Network for Multimodal Document-Level Relation Extraction

Lingxing Kong
Jiuliang Wang
Zheng Ma
Qifeng Zhou
Jianbing Zhang
Liang He
Jiajun Chen

Document-level relation extraction aims to extract entity relations that span across multiple sentences. This task faces two critical issues: long dependency and mention selection. Prior works address the above problems from the textual perspective, however, it is hard to handle these problems solely based on text information. In this paper, we leverage video information to provide additional evidence for understanding long dependencies and offer a wider perspective for identifying relevant mentions, thus giving rise to a new task named Multimodal Document-level Relation Extraction (MDocRE). To tackle this new task, we construct a human-annotated dataset including documents and relevant videos, which, to the best of our knowledge, is the first document-level relation extraction dataset equipped with video clips. We also propose a hierarchical framework to learn interactions between different dependency levels and a textual-guided transformer architecture that incorporates both textual and video modalities. In addition, we utilize a mention gate module to address the mention-selection problem in both modalities. Experiments on our proposed dataset show that 1) incorporating video information greatly improves model performance; 2) our hierarchical framework has state-of-the-art results compared with both unimodal and multimodal baselines; 3) through collaborating with video information, our model better solves the long-dependency and mention-selection problems.

PDF Details DOI

JMLR Journal 2021 Journal Article

Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit

Tao Luo
Zhi-Qin John Xu
Zheng Ma
Yaoyu Zhang

How neural network behaves during the training over different choices of hyperparameters is an important question in the study of neural networks. In this work, inspired by the phase diagram in statistical mechanics, we draw the phase diagram for the two-layer ReLU neural network at the infinite-width limit for a complete characterization of its dynamical regimes and their dependence on hyperparameters related to initialization. Through both experimental and theoretical approaches, we identify three regimes in the phase diagram, i.e., linear regime, critical regime and condensed regime, based on the relative change of input weights as the width approaches infinity, which tends to $0$, $O(1)$ and $+\infty$, respectively. In the linear regime, NN training dynamics is approximately linear similar to a random feature model with an exponential loss decay. In the condensed regime, we demonstrate through experiments that active neurons are condensed at several discrete orientations. The critical regime serves as the boundary between above two regimes, which exhibits an intermediate nonlinear behavior with the mean-field model as a typical example. Overall, our phase diagram for the two-layer ReLU NN serves as a map for the future studies and is a first step towards a more systematical investigation of the training behavior and the implicit regularization of NNs of different structures. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

PDF Details

JBHI Journal 2020 Journal Article

Automatic Medical Code Assignment via Deep Learning Approach for Intelligent Healthcare

Fei Teng
Zheng Ma
Jie Chen
Ming Xiao
Lufei Huang

With the development of healthcare 4. 0, there has been an explosion in the amount of data such as image, medical text, physiological signals, lab tests, etc. Among them, medical records provide a complete picture of the associated clinical events. However, the processing of medical texts is difficult because they are structurally free, diverse in style, and have subjective factors. Assigning metadata codes from the International Classification of Diseases (ICD) presents a standardized way of indicating diagnoses and procedures, so it becomes a mandatory process for understanding medical records to make better clinical and financial decisions. Such a manual encoding task is time-consuming, error-prone and expensive. In this paper, we proposed a deep learning approach and a medical topic mining method to automatically predict ICD codes from text-free medical records. The result of the F1 score on Medical Information Mart for Intensive Care (MIMIC-III) dataset increases by 5% over the state of art. It also suitable for multiple ICD versions and languages. For the specific disease, atrial fibrillation, the F1 score is up to 96% and 93. 3% using in-house ICD-10 datasets and MIMIC-III datasets, respectively. We developed an Artificial Intelligence based coding system, which can greatly improve the efficiency and accuracy of human coders, and meanwhile accelerate the secondary use for clinical informatics.

Details DOI

ICML Conference 2020 Conference Paper

Haar Graph Pooling

Yu Guang Wang 0001
Ming Li 0065
Zheng Ma
Guido Montúfar
Xiaosheng Zhuang
Yanan Fan

Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar transforms — \emph{HaarPooling}. HaarPooling implements a cascade of pooling operations; it is computed by following a sequence of clusterings of the input graph. A HaarPooling layer transforms a given input graph to an output graph with a smaller node number and the same feature dimension; the compressive Haar transform filters out fine detail information in the Haar wavelet domain. In this way, all the HaarPooling layers together synthesize the features of any given input graph into a feature vector of uniform size. Such transforms provide a sparse characterization of the data and preserve the structure information of the input graph. GNNs implemented with standard graph convolution layers and HaarPooling layers achieve state of the art performance on diverse graph classification and regression problems.

Details

TIST Journal 2020 Journal Article

Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing

Xiaoguang Tu
Zheng Ma
Jian Zhao
Guodong DU
Mei Xie
Jiashi Feng

Face anti-spoofing aims to detect presentation attack to face recognition--based authentication systems. It has drawn growing attention due to the high security demand. The widely adopted CNN-based methods usually well recognize the spoofing faces when training and testing spoofing samples display similar patterns, but their performance would drop drastically on testing spoofing faces of novel patterns or unseen scenes, leading to poor generalization performance. Furthermore, almost all current methods treat face anti-spoofing as a prior step to face recognition, which prolongs the response time and makes face authentication inefficient. In this article, we try to boost the generalizability and applicability of face anti-spoofing methods by designing a new generalizable face authentication CNN (GFA-CNN) model with three novelties. First, GFA-CNN introduces a simple yet effective total pairwise confusion loss for CNN training that properly balances contributions of all spoofing patterns for recognizing the spoofing faces. Second, it incorporate a fast domain adaptation component to alleviate negative effects brought by domain variation. Third, it deploys filter diversification learning to make the learned representations more adaptable to new scenes. In addition, the proposed GFA-CNN works in a multi-task manner—it performs face anti-spoofing and face recognition simultaneously. Experimental results on five popular face anti-spoofing and face recognition benchmarks show that GFA-CNN outperforms previous face anti-spoofing methods on cross-test protocols significantly and also well preserves the identity information of input face images.

Details DOI

NeurIPS Conference 2020 Conference Paper

Path Integral Based Convolution and Pooling for Graph Neural Networks

Zheng Ma
Junyu Xuan
Yu Guang Wang
Ming Li
Pietro Liò

Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs. Specifically, we consider a convolution operation that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. It generalizes the graph Laplacian to a new transition matrix we call \emph{maximal entropy transition} (MET) matrix derived from a path integral formalism. Importantly, the diagonal entries of the MET matrix are directly related to the subgraph centrality, thus lead to a natural and adaptive pooling mechanism. PAN provides a versatile framework that can be tailored for different graph data with varying sizes and structures. We can view most existing GNN architectures as special cases of PAN. Experimental results show that PAN achieves state-of-the-art performance on various graph classification/regression tasks, including a new benchmark dataset from statistical mechanics we propose to boost applications of GNN in physical sciences.

PDF Details

AAAI Conference 2019 Conference Paper

Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks

Yuenan Hou
Zheng Ma
Chunxiao Liu
Chen Change Loy

The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, these methods are susceptible to the presence of sharp road curves, challenging traffic conditions, strong shadows, and severe lighting changes. In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction. Specifically, we train our steering angle predictive model by distilling multi-layer knowledge from multiple heterogeneous auxiliary networks that perform related but different tasks, e.g., image segmentation or optical flow estimation. As opposed to multi-task learning, our method does not require expensive annotations of related tasks on the target set. This is made possible by applying contemporary off-the-shelf networks on the target set and mimicking their features in different layers after transformation. The auxiliary networks are discarded after training without affecting the runtime efficiency of our model. Our approach achieves a new state-of-the-art on Udacity and Comma.ai, outperforming the previous best by a large margin of 12.8% and 52.1%1, respectively. Encouraging results are also shown on Berkeley Deep Drive (BDD) dataset.

PDF Details