Graph neural networks (GNNs) have shown the power in representation learning over graph-structured user-item interaction data for collaborative filtering (CF) task. However, with their inherently recursive message propagation among neighboring nodes, existing GNN-based CF models may generate indistinguishable and inaccurate user (item) representations due to the over-smoothing and noise effect with low-pass Laplacian smoothing operators. In addition, the recursive information propagation with the stacked aggregators in the entire graph structures may result in poor scalability in practical applications. Motivated by these limitations, we propose a simple and effective collaborative filtering model (SimRec) that marries the power of knowledge distillation and contrastive learning. In SimRec, adaptive transferring knowledge is enabled between the teacher GNN model and a lightweight student network, to not only preserve the global collaborative signals, but also address the over-smoothing issue with representation recalibration. Empirical results on public datasets show that SimRec archives better efficiency while maintaining superior recommendation performance compared with various strong baselines. Our implementations are publicly available at: https://github.com/HKUDS/SimRec.

翻译：图神经网络（GNN）在图结构的用户-物品交互数据上展现了强大的表征学习能力，用于协同过滤（CF）任务。然而，由于其固有的相邻节点间递归消息传播机制，现有基于GNN的CF模型因低通拉普拉斯平滑算子导致的过度平滑与噪声效应，可能生成难以区分且不准确的用户（物品）表征。此外，全图结构中堆叠聚合器的递归信息传播可能导致实际应用中的可扩展性较差。受这些局限性的启发，我们提出一个简单而有效的协同过滤模型（SimRec），融合了知识蒸馏与对比学习的优势。在SimRec中，教师GNN模型与轻量级学生网络之间实现了自适应知识迁移，既能保留全局协同信号，又能通过表征校准解决过度平滑问题。在公开数据集上的实验结果表明，与多种强基线模型相比，SimRec在保持优异推荐性能的同时实现了更高效率。我们的实现代码已公开于：https://github.com/HKUDS/SimRec。