Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in Tencent

TL;DR

This paper introduces SocialNet, a novel method that combines social graph data with user behavior to improve video recommendations, especially for cold users, demonstrating significant offline and online performance gains.

Contribution

The paper proposes a two-stage social interest extraction algorithm and a user representation enhancement technique for better recommendations in cold user scenarios.

Findings

Superiority over baseline behavior-based models in offline tests.

Significant improvements in clicks and view time in real-world online experiments.

Effective integration of social interests with user behavior for recommendation enhancement.

Abstract

Despite recommender systems play a key role in network content platforms, mining the user's interests is still a significant challenge. Existing works predict the user interest by utilizing user behaviors, i.e., clicks, views, etc., but current solutions are ineffective when users perform unsettled activities. The latter ones involve new users, which have few activities of any kind, and sparse users who have low-frequency behaviors. We uniformly describe both these user-types as "cold users", which are very common but often neglected in network content platforms. To address this issue, we enhance the representation of the user interest by combining his social interest, e.g., friendship, following bloggers, interest groups, etc., with the activity behaviors. Thus, in this work, we present a novel algorithm entitled SocialNet, which adopts a two-stage method to progressively extract the coarse-grained and fine-grained social interest. Our technique then concatenates SocialNet's output with the original user representation to get the final user representation that combines behavior interests and social interests. Offline experiments on Tencent video's recommender system demonstrate the superiority over the baseline behavior-based model. The online experiment also shows a significant performance improvement in clicks and view time in the real-world recommendation system. The source code is available at https://github.com/Social4Rec/SocialNet.