Tools and experiments to analyze Graph Neural Networks' (GNNs) interpretability during training. Includes concept-based analysis, neuron evaluation, and visualizations to study accuracy-interpretability trade-offs. Tested on datasets like MUTAG and IMDB-Binary using advanced metrics and frameworks.
active 2025-01-14 → 2025-01-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 2 days from 2025-01-14 to 2025-01-15. Pushes: 19 total, peak 17 in a day. Pull requests: 30 total, peak 28 in a day. Issues: 29 total, peak 27 in a day. Comments: 3 total, peak 3 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| ashkanans | 81 | 19 | 30 | 3 |
Recent activity
Latest issues, pull requests and releases
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.