MUSE：面向异配图的多视图对比学习
MUSE: Multi-View Contrastive Learning for Heterophilic Graphs
AI总结：
针对异配图自监督学习效果受限问题，提出多视图对比学习模型MUSE，通过构建自我节点与邻域视图并利用信息融合控制器和交替训练方案，有效提升了节点分类与聚类性能。
摘要：
近年来，自监督学习已成为解决传统GNN中标签依赖和泛化性能差等问题的有前景的方法。然而，现有的自监督方法在异配图上的效果有限，这是由于同质性假设会导致相连节点具有相似的节点表示。在本研究中，我们提出了一种面向异配图的多视图对比学习模型，即MUSE。具体而言，我们通过对比学习增强的GNN分别构建两个视图，以捕获自我节点及其邻域的信息。然后我们整合这两个视图的信息来融合节点表示。利用融合对比来增强融合节点表示的有效性。此外，考虑到邻域上下文信息对信息融合的影响可能因不同的自我节点而异，我们采用信息融合控制器在局部和全局层面建模节点-邻域相似性的多样性。最后，采用交替训练方案以确保无监督节点表示学习和信息融合控制器能够相互促进。我们进行了广泛的实验来评估MUSE在9个基准数据集上的性能。结果表明了MUSE在节点分类和聚类任务上的有效性。
英文摘要：
In recent years, self-supervised learning has emerged as a promising approach in addressing the issues of label dependency and poor generalization performance in traditional GNNs. However, existing self-supervised methods have limited effectiveness on heterophilic graphs, due to the homophily assumption that results in similar node representations for connected nodes. In this work, we propose a multi-view contrastive learning model for heterophilic graphs, namely, MUSE. Specifically, we construct two views to capture the information of the ego node and its neighborhood by GNNs enhanced with contrastive learning, respectively. Then we integrate the information from these two views to fuse the node representations. Fusion contrast is utilized to enhance the effectiveness of fused node representations. Further, considering that the influence of neighboring contextual information on information fusion may vary across different ego nodes, we employ an information fusion controller to model the diversity of node-neighborhood similarity at both the local and global levels. Finally, an alternating training scheme is adopted to ensure that unsupervised node representation learning and information fusion controller can mutually reinforce each other. We conduct extensive experiments to evaluate the performance of MUSE on 9 benchmark datasets. Our results show the effectiveness of MUSE on both node classification and clustering tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
