@inproceedings{li-etal-2025-mutual,
    title = "A Mutual Information Perspective on Knowledge Graph Embedding",
    author = "Li, Jiang  and
      Su, Xiangdong  and
      Duo, Zehua  and
      Lan, Tian  and
      Guo, Xiaotao  and
      Gao, Guanglai",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1077/",
    pages = "22152--22166",
    ISBN = "979-8-89176-251-0",
    abstract = "Knowledge graph embedding techniques have emerged as a critical approach for addressing the issue of missing relations in knowledge graphs. However, existing methods often suffer from limitations, including high intra-group similarity, loss of semantic information, and insufficient inference capability, particularly in complex relation patterns such as 1-N and N-1 relations. To address these challenges, we introduce a novel KGE framework that leverages mutual information maximization to improve the semantic representation of entities and relations. By maximizing the mutual information between different components of triples, such as $(h, r)$ and $t$, or $(r, t)$ and $h$, the proposed method improves the model{'}s ability to preserve semantic dependencies while maintaining the relational structure of the knowledge graph. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach, with consistent performance improvements across various baseline models. Additionally, visualization analyses and case studies demonstrate the improved ability of the MI framework to capture complex relation patterns."
}