Iteratively Learning Representations for Unseen Entities with Inter-Rule Correlations

ACM International Conference on Information and Knowledge Management (CIKM), pp. 2534–2543

Abstract

Recent work on knowledge graph completion (KGC) focuses on acquiring embeddings of entities and relations in knowledge graphs. These embedding methods necessitate that all test entities be present during the training phase, resulting in a time-consuming retraining process for out-of-knowledge-graph (OOKG) entities. To tackle this predicament, current inductive methods employ graph neural networks (GNNs) to represent unseen entities by aggregating information of the known neighbors, and enhance the performance with additional information, such as attention mechanisms or logic rules. Nonetheless, Two key challenges continue to persist: (i) identifying inter-rule correlations to further facilitate the inference process, and (ii) capturing interactions among rule mining, rule inference, and embedding to enhance both rule and embedding learning.

Authors 7

1. Zihan Wang

   Shandong University · University of Amsterdam

   Affiliation as printed

   Shandong University & University of Amsterdam, Qingdao, China

2. Kai Zhao

   Georgia State University

   Affiliation as printed

   Georgia State University, Atlanta, GA, USA

3. Yongquan He

   Meituan (China)

   Affiliation as printed

   Meituan, Beijing, China

4. Zhumin Chen

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

5. Pengjie Ren

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

6. Maarten de Rijke

   University of Amsterdam

   Affiliation as printed

   University of Amsterdam, Amsterdam, Netherlands

7. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, Netherlands