Picture for Choong Jun Jin

Choong Jun Jin

Learning Graph Neural Networks with Noisy Labels

Add code
May 05, 2019
Hoang NT, Choong Jun Jin, Tsuyoshi Murata
Figure 1 for Learning Graph Neural Networks with Noisy Labels
Figure 2 for Learning Graph Neural Networks with Noisy Labels
Figure 3 for Learning Graph Neural Networks with Noisy Labels

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 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon