Discovering Invariant Rationales for Graph Neural Networks
“Discovering Invariant Rationales for Graph Neural Networks” (ICLR 2022) aims to train intrinsic interpretable Graph Neural Networks that are generalizable to out-of-distribution datasets. The core of this work lies in the construction of environments, i.e., interventional distributions, and thus discovering the causal features for rationalization. Installation Main packages: PyTorch >= 1.5.0, Pytorch Geometric >= 1.7.0, OGB >= 1.3.0. See requirements.txt for other packages. Data download Spurious-Motif: this dataset can be generated via spmotif_gen/spmotif.ipynb. Graph-SST2: this dataset can be downloaded here. […]
Read more