Genetic Meta-Structure Search for Recommendation on Heterogeneous Information Network

TL;DR

This paper introduces GEMS, a genetic algorithm-based method to automatically discover effective meta-structures for heterogeneous information network recommendation, outperforming manual designs and enhancing recommendation accuracy.

Contribution

GEMS automates meta-structure search for HIN recommendation using a genetic algorithm, reducing reliance on expert knowledge and manual design.

Findings

GEMS outperforms baseline methods in HIN recommendation tasks.

GEMS achieves over 6% performance gain compared to hand-crafted meta-paths.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

In the past decade, the heterogeneous information network (HIN) has become an important methodology for modern recommender systems. To fully leverage its power, manually designed network templates, i.e., meta-structures, are introduced to filter out semantic-aware information. The hand-crafted meta-structure rely on intense expert knowledge, which is both laborious and data-dependent. On the other hand, the number of meta-structures grows exponentially with its size and the number of node types, which prohibits brute-force search. To address these challenges, we propose Genetic Meta-Structure Search (GEMS) to automatically optimize meta-structure designs for recommendation on HINs. Specifically, GEMS adopts a parallel genetic algorithm to search meaningful meta-structures for recommendation, and designs dedicated rules and a meta-structure predictor to efficiently explore the search space. Finally, we propose an attention based multi-view graph convolutional network module to dynamically fuse information from different meta-structures. Extensive experiments on three real-world datasets suggest the effectiveness of GEMS, which consistently outperforms all baseline methods in HIN recommendation. Compared with simplified GEMS which utilizes hand-crafted meta-paths, GEMS achieves over $6\%$ performance gain on most evaluation metrics. More importantly, we conduct an in-depth analysis on the identified meta-structures, which sheds light on the HIN based recommender system design.