In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 12

Multi-view neighbor contrastive learning for node classification

Liu Junlong
Dong Jizhou
Wang Yidan
Hebei Key Laboratory of Machine Learning & Computational Intelligence, College of Mathematics & Information Science, Hebei University, Baoding Hebei 071002, China
DOI: 10.19734/j.issn.1001-3695.2025.05.0170

Abstract

The widespread application of graph contrastive learning (GCL) methods in node classification has effectively alleviated the reliance on label information. However, existing GCL methods tend to aggregate a large amount of information from dissimilar nodes in heterophilic graphs. Moreover, a potential conflict arises between the neighbor aggregation process of Graph Neural Networks (GNNs) and the optimization objectives of contrastive loss functions. To mitigate these issues, a theoretical analysis was conducted to investigate the causes of performance degradation in heterophilic graphs and the source of conflicts within graph contrastive learning. Based on this analysis, a novel node classification framework, Multi-View Neighbor Contrastive Learning (MVNCL) , is proposed. Specifically, MVNCL introduces a structure-reconstruction-based augmentation strategy that incorporates node similarity and class uncertainty to more effectively identify hard negative samples. This approach generates augmented views in which connected nodes are more likely to belong to the same class, thereby promoting effective feature aggregation. In addition, MVNCL designs a neighbor contrastive loss function that compares node representations across the original and augmented views, as well as with non-structural views. This design reduces the conflict between feature aggregation and the contrastive learning objective. Extensive experiments on five benchmark datasets demonstrate that MVNCL consistently outperforms existing methods on both homophilic and heterophilic graphs, offering an effective solution for node classification across diverse graph structures.

Foundation Support

河北省自然科学基金青年基金资助项目(A2024201031)
河北省自然科学基金资助项目(H2024201062)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.05.0170
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 12

Publish History

[2025-08-21] Accepted Paper

Cite This Article

刘俊龙, 董继洲, 王祎丹. 基于多视图邻居对比学习的节点分类方法 [J]. 计算机应用研究, 2025, 42 (12). (2025-08-21). https://doi.org/10.19734/j.issn.1001-3695.2025.05.0170. (Liu Junlong, Dong Jizhou, Wang Yidan. Multi-view neighbor contrastive learning for node classification [J]. Application Research of Computers, 2025, 42 (12). (2025-08-21). https://doi.org/10.19734/j.issn.1001-3695.2025.05.0170. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)