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.

Cite

Text

Nt et al. "Learning Graph Neural Networks with Noisy Labels." ICLR 2019 Workshops: LLD, 2019.

Markdown

[Nt et al. "Learning Graph Neural Networks with Noisy Labels." ICLR 2019 Workshops: LLD, 2019.](https://mlanthology.org/iclrw/2019/nt2019iclrw-learning/)

BibTeX

@inproceedings{nt2019iclrw-learning,
  title     = {{Learning Graph Neural Networks with Noisy Labels}},
  author    = {Nt, Hoang and Choong, Jun Jin and Murata, Tsuyoshi},
  booktitle = {ICLR 2019 Workshops: LLD},
  year      = {2019},
  url       = {https://mlanthology.org/iclrw/2019/nt2019iclrw-learning/}
}