Graph Neural Networks (GNNs) have been widely applied on a variety of real-world applications, such as social recommendation. However, existing GNN-based models on social recommendation suffer from serious problems of generalization and oversmoothness, because of the underexplored negative sampling method and the direct implanting of the off-the-shelf GNN models. In this paper, we propose a succinct multi-network GNN-based neural model (NeMo) for social recommendation. Compared with the existing methods, the proposed model explores a generative negative sampling strategy, and leverages both the positive and negative user-item interactions for users' interest propagation. The experiments show that NeMo outperforms the state-of-the-art baselines on various real-world benchmark datasets (e.g., by up to 38.8% in terms of NDCG@15).
@article{arxiv.2304.04994,
title = {Neural Multi-network Diffusion towards Social Recommendation},
author = {Boxin Du and Lihui Liu and Jiejun Xu and Fei Wang and Hanghang Tong},
journal= {arXiv preprint arXiv:2304.04994},
year = {2023}
}