Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques

被引:0
|
作者
Li, Chen [1 ]
Zheng, Haotian [2 ]
Sun, Yiping [3 ]
Wang, Cangqing [4 ]
Yu, Liqiang [5 ]
Chang, Che [6 ]
Tian, Xinyu [7 ]
Liu, Bo [8 ]
机构
[1] Univ Texas Dallas, Dallas, TX 30346 USA
[2] NYU, New York, NY 10012 USA
[3] Shanghai Jiao Tong Univ, Shanghai 200240, Peoples R China
[4] Boston Univ, Boston, MA 02215 USA
[5] Univ Chicago, Chicago, IL 60637 USA
[6] George Washington Univ, Washington, DC 20052 USA
[7] Georgia Inst Technol, Atlanta, GA 30332 USA
[8] Zhejiang Univ, Hangzhou 310058, Zhejiang, Peoples R China
来源
2024 4TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND INTELLIGENT SYSTEMS ENGINEERING, MLISE 2024 | 2024年
关键词
Knowledge Graph Reasoning; Reinforcement Learning; Reward Shaping; Transfer Learning;
D O I
10.1109/MLISE62164.2024.10674566
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the realm of computational knowledge representation, Knowledge Graph Reasoning (KG-R) stands at the forefront of facilitating sophisticated inferential capabilities across multifarious domains. The quintessence of this research elucidates the employment of reinforcement learning (RL) strategies, notably the REINFORCE algorithm, to navigate the intricacies inherent in multi-hop KG-R. This investigation critically addresses the prevalent challenges introduced by the inherent incompleteness of Knowledge Graphs (KGs), which frequently results in erroneous inferential outcomes, manifesting as both false negatives and misleading positives. By partitioning the Unified Medical Language System (UMLS) benchmark dataset into rich and sparse subsets, we investigate the efficacy of pre-trained BERT embeddings and Prompt Learning methodologies to refine the reward shaping process. This approach not only enhances the precision of multi-hop KG-R but also sets a new precedent for future research in the field, aiming to improve the robustness and accuracy of knowledge inference within complex KG frameworks. Our work contributes a novel perspective to the discourse on KG reasoning, offering a methodological advancement that aligns with the academic rigor and scholarly aspirations of the Natural journal, promising to invigorate further advancements in the realm of computational knowledge representation.
引用
收藏
页码:1 / 5
页数:5
相关论文
共 50 条
  • [1] Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
    Li, Chen
    Zheng, Haotian
    Sun, Yiping
    Wang, Cangqing
    Yu, Liqiang
    Chang, Che
    Tian, Xinyu
    Liu, Bo
    2024 4th International Conference on Machine Learning and Intelligent Systems Engineering, MLISE 2024, 2024, : 1 - 5
  • [2] Multi-Hop Knowledge Graph Reasoning with Reward Shaping
    Lin, Xi Victoria
    Socher, Richard
    Xiong, Caiming
    2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 3243 - 3253
  • [3] Multi-Hop Reasoning for Question Answering with Knowledge Graph
    Zhang, Jiayuan
    Cai, Yifei
    Zhang, Qian
    Cao, Zehao
    Cheng, Zhenrong
    Li, Dongmei
    Meng, Xianghao
    2021 IEEE/ACIS 20TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE (ICIS 2021-SUMMER), 2021, : 121 - 125
  • [4] CogKR: Cognitive Graph for Multi-Hop Knowledge Reasoning
    Du, Zhengxiao
    Zhou, Chang
    Yao, Jiangchao
    Tu, Teng
    Cheng, Letian
    Yang, Hongxia
    Zhou, Jingren
    Tang, Jie
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (02) : 1283 - 1295
  • [5] GaussianPath:A Bayesian Multi-Hop Reasoning Framework for Knowledge Graph Reasoning
    Wan, Guojia
    Du, Bo
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4393 - 4401
  • [6] ExKGR: Explainable Multi-hop Reasoning for Evolving Knowledge Graph
    Yan, Cheng
    Zhao, Feng
    Jin, Hai
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT I, 2022, : 153 - 161
  • [7] Attention-based Multi-hop Reasoning for Knowledge Graph
    Wang, Zikang
    Li, Linjing
    Zeng, Daniel Dajun
    Chen, Yue
    2018 IEEE INTERNATIONAL CONFERENCE ON INTELLIGENCE AND SECURITY INFORMATICS (ISI), 2018, : 211 - 213
  • [8] Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
    Ji, Haozhe
    Ke, Pei
    Huang, Shaohan
    Wei, Furu
    Zhu, Xiaoyan
    Huang, Minlie
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 725 - 736
  • [9] Dual view graph transformer networks for multi-hop knowledge graph reasoning
    Sun, Congcong
    Chen, Jianrui
    Shao, Zhongshi
    Huang, Junjie
    NEURAL NETWORKS, 2025, 186
  • [10] Multi-hop path reasoning over sparse temporal knowledge graphs based on path completion and reward shaping
    Meng, Xiangxi
    Bai, Luyi
    Hu, Jiahui
    Zhu, Lin
    INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (02)