Negative Metric Learning for Graphs
This addresses a key bottleneck in graph representation learning for tasks like node classification, though it appears incremental as it builds on existing contrastive learning frameworks.
The paper tackles the problem of false negatives degrading performance in graph contrastive learning by proposing a Negative Metric Learning enhanced GCL method, which achieves superior results on benchmarks as verified by experiments.
Graph contrastive learning (GCL) often suffers from false negatives, which degrades the performance on downstream tasks. The existing methods addressing the false negative issue usually rely on human prior knowledge, still leading GCL to suboptimal results. In this paper, we propose a novel Negative Metric Learning (NML) enhanced GCL (NML-GCL). NML-GCL employs a learnable Negative Metric Network (NMN) to build a negative metric space, in which false negatives can be distinguished better from true negatives based on their distance to anchor node. To overcome the lack of explicit supervision signals for NML, we propose a joint training scheme with bi-level optimization objective, which implicitly utilizes the self-supervision signals to iteratively optimize the encoder and the negative metric network. The solid theoretical analysis and the extensive experiments conducted on widely used benchmarks verify the superiority of the proposed method.