Modeling High-order Interactions across Multi-interests for Micro-video Recommendation
This work addresses micro-video recommendation for users on video platforms, but it is incremental as it builds on existing attention-based methods.
The paper tackled the problem of capturing user multi-level interests and dependencies between viewed micro-videos in micro-video recommendation, proposing a Self-over-Co Attention module that improved interest representation, with experimental results on public datasets verifying its usefulness.
Personalized recommendation system has become pervasive in various video platform. Many effective methods have been proposed, but most of them didn't capture the user's multi-level interest trait and dependencies between their viewed micro-videos well. To solve these problems, we propose a Self-over-Co Attention module to enhance user's interest representation. In particular, we first use co-attention to model correlation patterns across different levels and then use self-attention to model correlation patterns within a specific level. Experimental results on filtered public datasets verify that our presented module is useful.