You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This repository contains the official implementation of GSAT as described in the paper: [Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism](https://arxiv.org/abs/2201.12987) (ICML 2022) by Siqi Miao, Mia Liu, and Pan Li.
## News
- Jan. 21, 2023: Check out our latest paper [Learnable Randomness Injection (LRI)](https://openreview.net/forum?id=6u7mf9s2A9), which is recently accepted to ICLR 2023! In LRI, we further generalize the idea of GSAT and propose four datasets with ground-truth interpretation labels from real-world scientific applications.
- Jan. 21, 2023: Check out our latest paper [Learnable Randomness Injection (LRI)](https://openreview.net/forum?id=6u7mf9s2A9) with code [here](https://github.com/Graph-COM/LRI), which is recently accepted to ICLR 2023! In LRI, we further generalize the idea of GSAT and propose four datasets with ground-truth interpretation labels from real-world scientific applications (instead of synthetic datasets to evaluate interpretability!).
- Nov. 16, 2022: A bug was reported in the code when averaging edge attention weigts for undirected graphs, as pointed out by this [issue](https://github.com/Graph-COM/GSAT/issues/5). We have fixed this bug in the latest version of the code by this [PR](https://github.com/Graph-COM/GSAT/pull/8).
