Learning Graph Neural Networks with Noisy Labels

Abstract

We study the robustness to symmetric label noise of GNNs training procedures. By combining the nonlinear neural message-passing models (e.g. Graph Isomorphism Networks, GraphSAGE, etc.) with loss correction methods, we present a noise-tolerant approach for the graph classification task. Our experiments show that test accuracy can be improved under the artificial symmetric noisy setting.

5 pages, 4 figures, 3 tables; Appeared as a poster presentation at Limited Labeled Data (LLD) Workshop, ICLR 2019