Path-based algorithm over KG for recommendations

Leigh Eytan,

M.Sc. student at the department of Industrial Engineering in Tel Aviv University

31 March 2022, 12:00 PM, Room 206& via zoom

Abstract:
Incorporating knowledge graph into recommender systems has attracted increasing attention in recent years. By exploring the interlinks within a knowledge graph, the connectivity between users and items can be discovered as paths, which provide rich and complementary information to user-item interactions. In our research, we propose a path-based method over knowledge graphs, to derive recommendations and provide explanations. Our model uses Transformers to embed paths sequences over the graph and uses attention score to weight paths between entities, in order to extract possible explanations for the obtained recommendation. The model achieves good results in term of hit rate and nDCG, and outperformed baseline models.

Bio:
Leigh Eytan, M.Sc. student at the department of Industrial Engineering in Tel Aviv University, specializing in Data Science. Leigh holds a B.Sc. degree in Industrial Engineering from Tel Aviv University. Her research focuses on recommender systems over knowledge graph. The research is being supervised by Prof. Irad Ben Gal and Dr. Noam Koenigshtein.