Xin Peng

Xin Peng

Auto-generated profile, based on publicly available information

Xin Peng

National university of defense technology, Changsha, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XPXin Peng
Xin Peng
JCJieren Cheng
Jieren Cheng
XTXiangyan Tang
Xiangyan Tang
JLJingxin Liu
Jingxin Liu
JWJiahua Wu
Jiahua Wu
Graph representation is an important part of graph clustering. Recently, contrastive learning, which maximizes the mutual information between augmented graph views that share the same semantics, has become a popular and powerful paradigm for graph representation. However, in the process of patch contrasting, existing literature tends to learn all features into similar variables, i.e., representation collapse, leading to less discriminative graph representations. To tackle this problem, we propose a novel self-supervised learning method called dual contrastive learning network (DCLN), which aims to reduce the redundant information of learned latent variables in a dual manner. Specifically, the dual curriculum contrastive module (DCCM) is proposed, which approximates the node similarity matrix and feature similarity matrix to a high-order adjacency matrix and an identity matrix, respectively. By doing this, the informative information in high-order neighbors could be well collected and preserved while the irrelevant redundant features among representations could be eliminated, hence improving the discriminative capacity of the graph representation. Moreover, to alleviate the problem of sample imbalance during the contrastive process, we design a curriculum learning strategy, which enables the network to simultaneously learn reliable information from two levels. Extensive experiments on six benchmark datasets have demonstrated the effectiveness and superiority of the proposed algorithm compared with state-of-the-art methods.

23 November 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
WTWenxuan Tu
Wenxuan Tu
QLQing Liao
Qing Liao
SZSihang Zhou
Sihang Zhou
XPXin Peng
Xin Peng
CMChuan Ma
Chuan Ma
KHKunlun He
Kunlun He
Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferior representations for downstream evaluations. To address this issue, we propose a novel SGP method termed R obust m A sked g R aph auto E ncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space. Through both theoretical and empirical analyses, we have discovered that performing a joint mask-then-reconstruct strategy in both latent feature and raw data spaces could yield improved stability and performance. To this end, we elaborately design a masked latent feature completion scheme, which predicts latent features of masked nodes under the guidance of high-order sample correlations that are hard to be observed from the raw data perspective. Specifically, we first adopt a latent feature predictor to predict the masked latent features from the visible ones. Next, we encode the raw data of masked samples with a momentum graph encoder and subsequently employ the resulting representations to improve the predicted results through latent feature matching. Extensive experiments on seventeen datasets have demonstrated the effectiveness and robustness of RARE against state-of-the-art (SOTA) competitors across three downstream tasks.

4 October 2023 in Information Fusion
Verified
Journal Article
Closed access
XPXin Peng
Xin Peng
JCJieren Cheng
Jieren Cheng
XTXiangyan Tang
Xiangyan Tang
BZBin Zhang
Bin Zhang
WTWenxuan Tu
Wenxuan Tu

29 December 2021 in International Journal of Intelligent Systems
Verified
Journal Article
Closed access
PDF file
JCJieren Cheng
Jieren Cheng
XPXin Peng
Xin Peng
XTXiangyan Tang
Xiangyan Tang
WTWenxuan Tu
Wenxuan Tu
WXWenhang Xu
Wenhang Xu

9 April 2024 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
XPXin Peng
Xin Peng
JCJieren Cheng
Jieren Cheng
XTXiangyan Tang
Xiangyan Tang
ZDZiqi Deng
Ziqi Deng
WTWenxuan Tu
Wenxuan Tu
Neal XiongNeal Xiong
Neal Xiong
Semantic segmentation, which aims to accurately identify each pixel, is a meaningful and challenging task. Recently, we witness a strong tendency to improve model efficiency in low-computing applications. However, most real-time methods ignore hierarchical features and context information to improve efficiency, leading to a decrease in the accuracy of semantic segmentation. To this end, we propose a novel system named hierarchical semantic-aware network (HSNet) to refine multilevel context information. HSNet mainly has the following two core modules: 1) hierarchical feature refinement module (HFRM) and 2) cross-scale pyramid fusion module (CPFM). By aggregating hierarchical feature maps, the proposed HFRM learns multilevel feature representation to recover spatial details. Afterward, the dual attention mechanism is developed to refine features from both channel and spatial levels, thereby alleviating the multilevel semantic gap. Meanwhile, the CPFM, which fuses local and global context information in a cross-scale manner, is proposed to enrich semantic information to improve accuracy. Furthermore, HSNet is carefully designed to improve the efficiency of the model by reusing shallow features and reducing channel capacity. Extensive experiments show that our method is effective and superior in segmentation accuracy and inference speed compared with state-of-the-art methods.

24 April 2026 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
YQYihao Qin
Yihao Qin
NTNATIONAL UNIVERSITY OF TECHNOLOGY
NATIONAL UNIVERSITY OF TECHNOLOGY
YLYan Lei
Yan Lei
ZZZhuo Zhang
Zhuo Zhang
BLBo Lin
Bo Lin
XMXiaoguang Mao
Xiaoguang Mao
The software development process is characterized by an iterative cycle of continuous functionality implementation and debugging, essential for the enhancement of software quality and adaptability to changing requirements. This process incorporates two isolatedly studied tasks: Code Search (CS), which retrieves reference code from a code corpus to aid in code implementation, and Fault Localization (FL), which identifies code entities responsible for bugs within the software project to boost software debugging. The basic observation of this study is that these two tasks exhibit similarities since they both address search problems. Notably, CS techniques have demonstrated greater effectiveness than FL ones, possibly because of the precise semantic details of the required code offered by natural language queries, which are not readily accessible to FL methods. Drawing inspiration from this, we hypothesize that a fault localizer could achieve greater proficiency if semantic information about the buggy methods were made available. Based on this idea, we propose \(\texttt{CosFL}\) , an FL approach that decomposes the FL task into two steps: query generation , which describes the functionality of the problematic code in natural language, and fault retrieval , which uses CS to find program elements semantically related to the query, allowing for finishing the FL task from a CS perspective. Specifically, to depict the buggy functionalities and generate high-quality queries, \(\texttt{CosFL}\) extensively harnesses the code analysis, semantic comprehension, text generation, and decision-making capabilities of LLMs. Moreover, to enhance the accuracy of CS, \(\texttt{CosFL}\) captures varying levels of context information and employs a multi-granularity CS strategy, which facilitates a more precise identification of buggy methods from a holistic view. The evaluation on 835 real bugs from 23 Java projects shows that \(\texttt{CosFL}\) successfully localizes 324 bugs within Top-1, which significantly outperforms the state-of-the-art approaches by 26.6%–57.3%. The ablation study and sensitivity analysis further validate the importance of different components and the robustness of \(\texttt{CosFL}\) across different backend models.