ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation

TL;DR

ConsisRec improves social recommendation by addressing social inconsistency in GNNs, using neighbor sampling based on consistency scores and relation attention to enhance aggregation, leading to better performance on real datasets.

Contribution

Introduces a novel neighbor sampling and relation attention mechanism to tackle social inconsistency in GNN-based social recommendation.

Findings

Effective in real-world datasets

Outperforms baseline models

Addresses social inconsistency problem

Abstract

Social recommendation aims to fuse social links with user-item interactions to alleviate the cold-start problem for rating prediction. Recent developments of Graph Neural Networks (GNNs) motivate endeavors to design GNN-based social recommendation frameworks to aggregate both social and user-item interaction information simultaneously. However, most existing methods neglect the social inconsistency problem, which intuitively suggests that social links are not necessarily consistent with the rating prediction process. Social inconsistency can be observed from both context-level and relation-level. Therefore, we intend to empower the GNN model with the ability to tackle the social inconsistency problem. We propose to sample consistent neighbors by relating sampling probability with consistency scores between neighbors. Besides, we employ the relation attention mechanism to assign consistent relations with high importance factors for aggregation. Experiments on two real-world datasets verify the model effectiveness.