# Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

## TL;DR

This paper introduces dual graph attention networks that dynamically model social effects in recommender systems, incorporating user and item domain effects with a policy-based fusion strategy, leading to improved recommendation accuracy.

## Contribution

It proposes a novel dual graph attention network framework with dynamic, context-aware social effect modeling and a policy-based fusion strategy for better social recommendation performance.

## Key findings

- Significant improvement in recommendation accuracy over state-of-the-art methods
- Effective modeling of dynamic social effects in user and item domains
- Validation on benchmark and commercial datasets

## Abstract

Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods. However, most existing models assume that social effects from friend users are static and under the forms of constant weights or fixed constraints. To relax this strong assumption, in this paper, we propose dual graph attention networks to collaboratively learn representations for two-fold social effects, where one is modeled by a user-specific attention weight and the other is modeled by a dynamic and context-aware attention weight. We also extend the social effects in user domain to item domain, so that information from related items can be leveraged to further alleviate the data sparsity problem. Furthermore, considering that different social effects in two domains could interact with each other and jointly influence user preferences for items, we propose a new policy-based fusion strategy based on contextual multi-armed bandit to weigh interactions of various social effects. Experiments on one benchmark dataset and a commercial dataset verify the efficacy of the key components in our model. The results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art social recommendation methods.