{"id":39687169,"url":"https://github.com/diegoantognini/pyGAT","last_synced_at":"2026-01-26T19:03:44.991Z","repository":{"id":37447154,"uuid":"123565023","full_name":"diegoantognini/pyGAT","owner":"diegoantognini","description":"Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)","archived":false,"fork":false,"pushed_at":"2023-07-06T21:23:03.000Z","size":212,"stargazers_count":3111,"open_issues_count":47,"forks_count":705,"subscribers_count":14,"default_branch":"master","last_synced_at":"2026-01-22T21:26:20.583Z","etag":null,"topics":["attention-mechanism","graph-attention-networks","neural-networks","python","pytorch","self-attention"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/diegoantognini.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-03-02T10:20:26.000Z","updated_at":"2026-01-22T14:28:49.000Z","dependencies_parsed_at":"2024-01-12T18:38:29.967Z","dependency_job_id":"3ef39fc1-23d0-41fc-b77a-355bf038dd62","html_url":"https://github.com/diegoantognini/pyGAT","commit_stats":null,"previous_names":["diegoantognini/pygat"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/diegoantognini/pyGAT","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegoantognini%2FpyGAT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegoantognini%2FpyGAT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegoantognini%2FpyGAT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegoantognini%2FpyGAT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/diegoantognini","download_url":"https://codeload.github.com/diegoantognini/pyGAT/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegoantognini%2FpyGAT/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28785172,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-26T13:55:28.044Z","status":"ssl_error","status_checked_at":"2026-01-26T13:55:26.068Z","response_time":59,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attention-mechanism","graph-attention-networks","neural-networks","python","pytorch","self-attention"],"created_at":"2026-01-18T10:01:03.640Z","updated_at":"2026-01-26T19:03:44.982Z","avatar_url":"https://github.com/diegoantognini.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Pytorch Graph Attention Network\n\nThis is a pytorch implementation of the Graph Attention Network (GAT)\nmodel presented by Veličković et. al (2017, https://arxiv.org/abs/1710.10903).\n\nThe repo has been forked initially from https://github.com/tkipf/pygcn. The official repository for the GAT (Tensorflow) is available in https://github.com/PetarV-/GAT. Therefore, if you make advantage of the pyGAT model in your research, please cite the following:\n\n```\n@article{\n  velickovic2018graph,\n  title=\"{Graph Attention Networks}\",\n  author={Veli{\\v{c}}kovi{\\'{c}}, Petar and Cucurull, Guillem and Casanova, Arantxa and Romero, Adriana and Li{\\`{o}}, Pietro and Bengio, Yoshua},\n  journal={International Conference on Learning Representations},\n  year={2018},\n  url={https://openreview.net/forum?id=rJXMpikCZ},\n  note={accepted as poster},\n}\n```\n\nThe branch **master** contains the implementation from the paper. The branch **similar_impl_tensorflow** the implementation from the official Tensorflow repository.\n\n# Performances\n\nFor the branch **master**, the training of the transductive learning on Cora task on a Titan Xp takes ~0.9 sec per epoch and 10-15 minutes for the whole training (~800 epochs). The final accuracy is between 84.2 and 85.3 (obtained on 5 different runs). For the branch **similar_impl_tensorflow**, the training takes less than 1 minute and reach ~83.0.\n\nA small note about initial sparse matrix operations of https://github.com/tkipf/pygcn: they have been removed. Therefore, the current model take ~7GB on GRAM.\n\n# Sparse version GAT\n\nWe develop a sparse version GAT using pytorch. There are numerically instability because of softmax function. Therefore, you need to initialize carefully. To use sparse version GAT, add flag `--sparse`. The performance of sparse version is similar with tensorflow. On a Titan Xp takes 0.08~0.14 sec.\n\n# Requirements\n\npyGAT relies on Python 3.5 and PyTorch 0.4.1 (due to torch.sparse_coo_tensor).\n\n# Issues/Pull Requests/Feedbacks\n\nDon't hesitate to contact for any feedback or create issues/pull requests.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiegoantognini%2FpyGAT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdiegoantognini%2FpyGAT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiegoantognini%2FpyGAT/lists"}