PyTorch implementation of Graph Matching Networks, e.g., Graph Matching with Bi-level Noisy Correspondence (COMMON, ICCV 2023), Graph Matching Networks for Learning the Similarity of Graph Structured Objects (GMN, ICML 2019).
active 2023-08-15 → 2026-04-19 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 979 days from 2023-08-15 to 2026-04-19. Pushes: 1 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 4 total, peak 1 in a day. Comments: 11 total, peak 4 in a day. Stars: 101 total, peak 2 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Lin-Yijie | 9 | 1 | 0 | 8 |
| Tp-mi | 2 | 0 | 0 | 1 |
| tsjain | 2 | 0 | 0 | 0 |
| zztian007 | 2 | 0 | 0 | 1 |
| ActExaggeratedly | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#10Lin-Yijie2024-10-09 08:36A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
- Issue comment#10ActExaggeratedly2024-10-09 08:22A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
- Issue comment#13Lin-Yijie2024-06-13 02:19Scaling of edge network with 0.1
- Issue comment#12Lin-Yijie2024-06-13 01:58Will ReLU be ever called for single dimensional node_state_dim?
- Issue#13tsjain2024-06-12 20:37Scaling of edge network with 0.1
- Issue#12tsjain2024-06-10 22:22Will ReLU be ever called for single dimensional node_state_dim?
- Issue comment#11Lin-Yijie2024-04-20 08:54Thanks for your excellent work, but why can't I find any work related to adding noise in the code?
- Issue comment#11Tp-mi2024-04-14 09:57Thanks for your excellent work, but why can't I find any work related to adding noise in the code?
- Issue comment#11Lin-Yijie2024-04-14 09:21Thanks for your excellent work, but why can't I find any work related to adding noise in the code?
- Issue#11Tp-mi2024-04-14 07:59Thanks for your excellent work, but why can't I find any work related to adding noise in the code?
- Issue comment#10Lin-Yijie2024-01-27 03:11A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
- Issue comment#10Lin-Yijie2024-01-27 03:05A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
- Issue comment#10zztian0072024-01-27 02:43A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
- Issue comment#10Lin-Yijie2024-01-27 01:51A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
- Issue#10zztian0072024-01-26 13:06A runtime error reported when executing the loss.backward(torch.ones_like(loss)) line
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 101 stars here means stars gained during the window, not the repo's star count.