Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation

TL;DR

This paper introduces MoSAN, a neural network architecture that models dynamic group decision-making by capturing fine-grained interactions among group members, leading to improved group recommendation performance.

Contribution

The paper presents a novel Medley of Sub-Attention Networks (MoSAN) architecture that effectively models group dynamics for recommendation tasks, outperforming existing methods.

Findings

MoSAN achieves state-of-the-art performance on group recommendation benchmarks.

MoSAN significantly outperforms standard baseline models.

The model effectively captures intricate group member interactions.

Abstract

This paper proposes Medley of Sub-Attention Networks (MoSAN), a new novel neural architecture for the group recommendation task. Group-level recommendation is known to be a challenging task, in which intricate group dynamics have to be considered. As such, this is to be contrasted with the standard recommendation problem where recommendations are personalized with respect to a single user. Our proposed approach hinges upon the key intuition that the decision making process (in groups) is generally dynamic, i.e., a user's decision is highly dependent on the other group members. All in all, our key motivation manifests in a form of an attentive neural model that captures fine-grained interactions between group members. In our MoSAN model, each sub-attention module is representative of a single member, which models a user's preference with respect to all other group members. Subsequently, a Medley of Sub-Attention modules is then used to collectively make the group's final decision. Overall, our proposed model is both expressive and effective. Via a series of extensive experiments, we show that MoSAN not only achieves state-of-the-art performance but also improves standard baselines by a considerable margin.