用于噪声节点分类的低秩正则化与低秩注意力图对比学习
Graph Contrastive Learning with Low-Rank Regularization and Low-Rank Attention for Noisy Node Classification
AI总结：
针对图数据噪声损害GNNs性能的问题，提出两阶段直推式学习方法GCL-LRR及其改进版GCL-LR-Attention，通过低秩正则化与低秩注意力提升节点分类的鲁棒性和泛化能力。
摘要：
图神经网络（GNNs）在学习节点表示方面取得了显著成功，并在节点分类等任务中展现出强大的性能。然而，最近的发现表明，现实世界图数据中存在的噪声会严重损害GNNs的有效性。为了应对这一挑战，我们引入了一种鲁棒且创新的节点表示学习方法，名为低秩正则化图对比学习（GCL-LRR），它遵循一个用于节点分类的两阶段直推式学习框架。在第一阶段，GCL-LRR编码器通过原型对比学习进行优化，同时引入低秩正则化目标。在第二阶段，GCL-LRR生成的表示被线性直推式分类器用于预测图中未标记节点的标签。我们的GCL-LRR受到图数据及其标签的低频特性（LFP）启发，并在理论上受到我们为直推式学习提出的紧致泛化界的驱动。据我们所知，我们的理论结果是最早从理论上证明低秩正则化在直推式学习中优势的研究之一，这也得到了强有力的实证结果支持。为了进一步提升GCL-LRR的性能，我们提出了一个改进模型，名为GCL-LR-Attention，它将一个新颖的LR-Attention层引入GCL-LRR。GCL-LR-Attention降低了GCL-LRR的核复杂度，并有助于获得更紧的泛化界，从而带来性能提升。在标准基准数据集上的广泛评估证明了GCL-LRR和GCL-LR-Attention在学习有意义的节点表示方面的有效性和鲁棒性。代码可在https://github.com/Statistical-Deep-Learning/GCL-LR-Attention获取。
英文摘要：
Graph Neural Networks (GNNs) have achieved remarkable success in learning node representations and have shown strong performance in tasks such as node classification. However, recent findings indicate that the presence of noise in real-world graph data can substantially impair the effectiveness of GNNs. To address this challenge, we introduce a robust and innovative node representation learning method named Graph Contrastive Learning with Low-Rank Regularization, or GCL-LRR, which follows a two-stage transductive learning framework for node classification. In the first stage, the GCL-LRR encoder is optimized through prototypical contrastive learning while incorporating a low-rank regularization objective. In the second stage, the representations generated by GCL-LRR are employed by a linear transductive classifier to predict the labels of unlabeled nodes within the graph. Our GCL-LRR is inspired by the Low Frequency Property (LFP) of the graph data and its labels, and it is also theoretically motivated by our sharp generalization bound for transductive learning. To the best of our knowledge, our theoretical result is among the first to theoretically demonstrate the advantage of low-rank regularization in transductive learning, which is also supported by strong empirical results. To further enhance the performance of GCL-LRR, we present an improved model named GCL-LR-Attention, which incorporates a novel LR-Attention layer into GCL-LRR. GCL-LR-Attention reduces the kernel complexity of GCL-LRR and contributes to a tighter generalization bound, leading to improved performance. Extensive evaluations on standard benchmark datasets evidence the effectiveness and robustness of both GCL-LRR and GCL-LR-Attention in learning meaningful node representations. The code is available at https://github.com/Statistical-Deep-Learning/GCL-LR-Attention.
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。
