App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 8

Semantic-enhanced adversarial RL for multi-hop reasoning over knowledge graphs

Zhai Shepinga,b
Liu Xuea
Huang Zhaoa
Yang Ruia
a. School of Computer Science & Technology, b. Shaanxi Key Laboratory of Network Data Analysis & Intelligent Processing, Xi'an University of Posts & Telecommunications, Xi'an 710121, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0508

Abstract

Reinforcement learning-based multi-hop knowledge graph reasoning on large-scale graphs faced action space expansion, semantic drift, and sparse rewards. These problems made reasoning paths unstable. They also produced spuriously correlated paths. To alleviate these problems, this study proposed SEARL-KG. SEARL-KG is a semantic-enhanced adversarial reinforcement reasoning model. At the state representation level, the model fused structural embeddings with entity textual representations through a gating mechanism. At the decision-making level, the model applied a semantic-concept consistency constraint. This constraint filtered and reweighted candidate actions. At the optimization level, the model introduced adversarial rewards and multi-source reward shaping. These strategies improved path quality. Experimental results showed that SEARL-KG significantly improved MRR, Hits@1, and Hits@3 over baseline models on the FB15k-237 and WN18RR datasets. These results demonstrate the effectiveness of semantic constraints and adversarial shaping in improving reasoning performance and path reliability.

Foundation Support

国家自然科学基金资助项目(61373116):国家级大学生创新创业计划训练项目(202411664067)
陕西省大学生创新创业训练计划项目(S202411664140)
陕西省重点研发计划项目(2025SF-YBXM-528、2022GY-038)
陕西省教育厅科学研究计划项目(18,JK0697)
陕西省社会科学基金资助项目(2016N008)
工业和信息化部通信软科学项目(2018-R-26)
西安市社会科学规划基金资助项目(17X63)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0508
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 8

Publish History

[2026-04-22] Accepted Paper

Cite This Article

翟社平, 刘雪, 黄朝, 等. 基于语义增强的对抗强化知识图谱多跳路径推理 [J]. 计算机应用研究, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0508. (Zhai Sheping, Liu Xue, Huang Zhao, et al. Semantic-enhanced adversarial RL for multi-hop reasoning over knowledge graphs [J]. Application Research of Computers, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0508. )

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)