Combating Bilateral Edge Noise for Robust Link Prediction. (arXiv:2311.01196v1 [cs.LG])

Although link prediction on graphs has achieved great success with the
development of graph neural networks (GNNs), the potential robustness under the
edge noise is still less investigated. To close this gap, we first conduct an
empirical study to disclose that the edge noise bilaterally perturbs both input
topology and target label, yielding severe performance degradation and
representation collapse. To address this dilemma, we propose an
information-theory-guided principle, Robust Graph Information Bottleneck
(RGIB), to extract reliable supervision signals and avoid …

arxiv development edge gap gnns graph graph neural networks graphs link prediction networks neural networks noise prediction robustness study success the edge topology