Search-based Time-Aware Graph-Enhanced Recommendation with Sequential Behavior Data

Abstract

Extending from sequential recommendation models, in this paper, we present a novel framework named S earch-based T ime- A ware Rec ommendation (STARec) , which first retrieves the historical behaviors of the given user through a search-based retriever, and then captures the user’s evolving demands over time through a time-aware sequential network. We notice that the key insight of STARec is to use the feature and labels to augment the representations, and thus the effectiveness of STARec relies on the acquisition of rich browsing records of the target user and powerful representation of each browsed item and thus its performance could heavily drop regarding long-tail users and items. To this end, we extend STARec by constructing a graph upon the user-item interactions and leveraging the graph structure to enhance the representation learning. We call this extended version S earch-based T ime- A ware G raph- E nhanced Recommendation (STAGE) . We conduct extensive experiments on three real-world datasets and STARec achieves consistent superiority. We further compare STAGE against STARec long-tail users and our results demonstrate that STAGE could outperform STARec at most cases. Results of online A/B tests show that STARec and STAGE achieve an average CTR improvement of around 6% and 1.5% in the two main item recommendation scenarios respectively.