LegalGNN: Legal Information Enhanced Graph Neural Network for Recommendation

被引:22
|
作者
Yang, Jun [1 ]
Ma, Weizhi [1 ]
Zhang, Min [1 ]
Zhou, Xin [2 ]
Liu, Yiqun [1 ]
Ma, Shaoping [1 ]
机构
[1] Tsinghua Univ, 30 Shuangqing Rd, Beijing, Peoples R China
[2] IBM Res, Beijing, Peoples R China
基金
中国博士后科学基金;
关键词
Legal information recommendation; heterogeneous environments; heterogeneous information network; graph neural network;
D O I
10.1145/3469887
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recommendation in legal scenario (Legal-Rec) is a specialized recommendation task that aims to provide potential helpful legal documents for users. While there are mainly three differences compared with traditional recommendation: (1) Both the structural connections and textual contents of legal information are important in the Legal-Rec scenario, which means feature fusion is very important here. (2) Legal-Rec users prefer the newest legal cases (the latest legal interpretation and legal practice), which leads to a severe new-item problem. (3) Different from users in other scenarios, most Legal-Rec users are expert and domain-related users. They often concentrate on several topics and have more stable information needs. So it is important to accurately model user interests here. To the best of our knowledge, existing recommendation work cannot handle these challenges simultaneously. To address these challenges, we propose a legal information enhanced graph neural network-based recommendation framework (LegalGNN). First, a unified legal content and structure representation model is designed for feature fusion, where the Heterogeneous Legal Information Network (HLIN) is constructed to connect the structural features (e.g., knowledge graph) and contextual features (e.g., the content of legal documents) for training. Second, to model user interests, we incorporate the queries users issued in legal systems into the HLIN and link them with both retrieved documents and inquired users. This extra information is not only helpful for estimating user preferences, but also valuable for cold users/items (with less interaction history) in this scenario. Third, a graph neural network with relational attention mechanism is applied to make use of high-order connections in HLIN for Legal-Rec. Experimental results on a real-world legal dataset verify that LegalGNN outperforms several state-of-the-art methods significantly. As far as we know, LegalGNN is the first graph neural model for legal recommendation.
引用
收藏
页数:29
相关论文
共 50 条
  • [41] Graph neural network for recommendation in complex and quaternion spaces
    Longcan Wu
    Daling Wang
    Shi Feng
    Xiangmin Zhou
    Yifei Zhang
    Ge Yu
    World Wide Web, 2023, 26 (6) : 3945 - 3964
  • [42] Self-Propagation Graph Neural Network for Recommendation
    Yu, Wenhui
    Lin, Xiao
    Liu, Jinfei
    Ge, Junfeng
    Ou, Wenwu
    Qin, Zheng
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2022, 34 (12) : 5993 - 6002
  • [43] A Social Recommendation Algorithm Based on Graph Neural Network
    Lyu Y.-X.
    Hao S.
    Qiao G.-T.
    Xing Y.
    Dongbei Daxue Xuebao/Journal of Northeastern University, 2024, 45 (01): : 10 - 17
  • [44] Graph Convolutional Neural Network for Multimodal Movie Recommendation
    Mondal, Prabir
    Chakder, Daipayan
    Raj, Subham
    Saha, Sriparna
    Onoe, Naoyuki
    38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023, 2023, : 1633 - 1640
  • [45] KerGNNT: an interpretable graph neural network recommendation model
    Liang, Shengbin
    Ma, Jinfeng
    Sun, Fuqi
    Chen, Tingting
    Lu, Xixi
    Ren, Shuanglong
    KNOWLEDGE AND INFORMATION SYSTEMS, 2025,
  • [46] A heterogeneous graph neural network model for list recommendation
    Yang, Wenchuan
    Li, Jichao
    Tan, Suoyi
    Tan, Yuejin
    Lu, Xin
    KNOWLEDGE-BASED SYSTEMS, 2023, 277
  • [47] Graph neural network for recommendation in complex and quaternion spaces
    Wu, Longcan
    Wang, Daling
    Feng, Shi
    Zhou, Xiangmin
    Zhang, Yifei
    Yu, Ge
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2023, 26 (06): : 3945 - 3964
  • [48] Disentangled Hierarchical Attention Graph Neural Network for Recommendation
    He, Weijie
    Ouyang, Yuanxin
    Peng, Keqin
    Rong, Wenge
    Xiong, Zhang
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT I, ICIC 2024, 2024, 14875 : 415 - 426
  • [49] Complementary Product Recommendation Using Graph Neural Network
    Weijun, Ni
    Shujuan, Ji
    Yongquan, Liang
    Computer Engineering and Applications, 2024, 60 (10) : 292 - 300
  • [50] FedGR: Federated Graph Neural Network for Recommendation Systems
    Ma, Chuang
    Ren, Xin
    Xu, Guangxia
    He, Bo
    AXIOMS, 2023, 12 (02)