🤖 AI Summary
To address item-side unfairness and popularity bias in graph neural recommendation, this paper proposes HetroFair—a novel fair recommendation framework. Methodologically, HetroFair jointly integrates heterogeneity modeling and fairness constraints into a GCN architecture for the first time; designs a degree-agnostic, fairness-aware attention mechanism to decouple node-degree effects from neighborhood aggregation; and introduces a fine-grained heterogeneous feature weighting strategy for adaptive fusion of multi-source features. Extensive experiments on six real-world datasets demonstrate that HetroFair effectively mitigates item exposure unfairness and long-tail bias while improving recommendation quality—achieving up to a 12.7% improvement in Recall@20. The implementation is publicly available.
📝 Abstract
In recent years, graph neural networks (GNNs) have become a popular tool to improve the accuracy and performance of recommender systems. Modern recommender systems are not only designed to serve end users, but also to benefit other participants, such as items and item providers. These participants may have different or conflicting goals and interests, which raises the need for fairness and popularity bias considerations. GNN-based recommendation methods also face the challenges of unfairness and popularity bias, and their normalization and aggregation processes suffer from these challenges. In this paper, we propose a fair GNN-based recommender system, called HetroFair, to improve item-side fairness. HetroFair uses two separate components to generate fairness-aware embeddings: i) Fairness-aware attention, which incorporates the dot product in the normalization process of GNNs to decrease the effect of nodes' degrees. ii) Heterophily feature weighting, to assign distinct weights to different features during the aggregation process. To evaluate the effectiveness of HetroFair, we conduct extensive experiments over six real-world datasets. Our experimental results reveal that HetroFair not only alleviates unfairness and popularity bias on the item side but also achieves superior accuracy on the user side. Our implementation is publicly available at https://github.com/NematGH/HetroFair.