Hierarchical Context enabled Recurrent Neural Network for Recommendation

TL;DR

This paper introduces HCRNN, a hierarchical context-based RNN model that effectively captures long-term, local, and temporary user interests for improved sequential recommendation performance.

Contribution

The paper proposes a novel hierarchical context structure and gate mechanism for RNNs, enhancing long-term interest retention and interest drift modeling in recommendation systems.

Findings

HCRNN outperforms existing models on CiteULike, MovieLens, and LastFM datasets.

Hierarchical context improves modeling of user interest transitions.

Bi-channel attention effectively utilizes hierarchical context.

Abstract

A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recommendation system still suffer from the long-term dependency and the interest drifts. To resolve these challenges, we suggest HCRNN with three hierarchical contexts of the global, the local, and the temporary interests. This structure is designed to withhold the global long-term interest of users, to reflect the local sub-sequence interests, and to attend the temporary interests of each transition. Besides, we propose a hierarchical context-based gate structure to incorporate our \textit{interest drift assumption}. As we suggest a new RNN structure, we support HCRNN with a complementary \textit{bi-channel attention} structure to utilize hierarchical context. We experimented the suggested structure on the sequential recommendation tasks with CiteULike, MovieLens, and LastFM, and our model showed the best performances in the sequential recommendations.