通过掩码对比学习提升异构图推荐的抗噪能力
Heterogeneous Graph Masked Contrastive Learning for Robust Recommendation
- 随机掩码增强异构图，降低节点对局部邻居的敏感性
- 跨视角对比学习同时捕捉局部与高阶结构特征
- 在三个真实数据集上显著优于现有方法
异构图神经网络（HGNNs）在利用辅助信息进行推荐任务方面表现优异。然而，基于元路径构建的图通常过于稠密且包含大量噪声边，HGNNs的传播机制会将少量噪声扩散至远距离邻近节点，从而影响众多节点的嵌入表示。为解决此问题，本文提出一种新型模型Masked Contrastive Learning（MCL），通过随机掩码策略对元路径构建的图进行增强，降低节点对特定邻居的依赖，提升嵌入鲁棒性。此外，MCL在异构信息网络（HIN）上从两个角度进行对比学习：一跳邻居和元路径邻居，以同时获取局部与高阶结构信息。在三个真实数据集上的实验验证了该方法在推荐性能上的优越性。
原文摘要 · Abstract (English)
Heterogeneous graph neural networks (HGNNs) have demonstrated their superiority in exploiting auxiliary information for recommendation tasks. However, graphs constructed using meta-paths in HGNNs are usually too dense and contain a large number of noise edges. The propagation mechanism of HGNNs propagates even small amounts of noise in a graph to distant neighboring nodes, thereby affecting numerous node embeddings. To address this limitation, we introduce a novel model, named Masked Contrastive Learning (MCL), to enhance recommendation robustness to noise. MCL employs a random masking strategy to augment the graph via meta-paths, reducing node sensitivity to specific neighbors and bolstering embedding robustness. Furthermore, MCL employs contrastive cross-view on a Heterogeneous Information Network (HIN) from two perspectives: one-hop neighbors and meta-path neighbors. This approach acquires embeddings capturing both local and high-order structures simultaneously for recommendation. Empirical evaluations on three real-world datasets confirm the superiority of our approach over existing recommendation methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。