{"id":13709006,"url":"https://github.com/junxia97/ProGCL","last_synced_at":"2025-05-06T15:31:59.880Z","repository":{"id":41574652,"uuid":"492433047","full_name":"junxia97/ProGCL","owner":"junxia97","description":"[ICML 2022] \"ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning\"","archived":false,"fork":false,"pushed_at":"2022-06-13T12:18:21.000Z","size":34,"stargazers_count":39,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-05-13T22:52:55.566Z","etag":null,"topics":["contrastive-learning","graph-neural-networks","graph-self-supervised-learning","hard-negative-mining","icml-2022"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/junxia97.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-05-15T08:46:00.000Z","updated_at":"2024-04-15T03:43:44.000Z","dependencies_parsed_at":"2022-09-19T00:31:56.596Z","dependency_job_id":null,"html_url":"https://github.com/junxia97/ProGCL","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junxia97%2FProGCL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junxia97%2FProGCL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junxia97%2FProGCL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junxia97%2FProGCL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/junxia97","download_url":"https://codeload.github.com/junxia97/ProGCL/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":213741483,"owners_count":15631789,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["contrastive-learning","graph-neural-networks","graph-self-supervised-learning","hard-negative-mining","icml-2022"],"created_at":"2024-08-02T23:00:35.024Z","updated_at":"2024-08-02T23:03:33.922Z","avatar_url":"https://github.com/junxia97.png","language":"Python","readme":"# ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning (ICML 2022)\nPyTorch implementation for [ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning](https://arxiv.org/abs/2110.02027) accepted by ICML 2022.\n## Requirements\n* Python 3.7.4\n* PyTorch 1.7.0\n* torch_geometric 1.5.0\n* tqdm\n## Training \u0026 Evaluation\nProGCL-weight:\n```\npython train.py --device cuda:0 --dataset Amazon-Computers --param local:amazon-computers.json --mode weight\n```\nProGCL-mix:\n```\npython train.py --device cuda:0 --dataset Amazon-Computers --param local:amazon-computers.json --mode mix\n```\n## Useful resources for Pretrained Graphs Neural Networks\n* The first comprehensive survey on this topic: [A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications](https://arxiv.org/abs/2202.07893v1)\n* [A curated list of must-read papers, open-source pretrained models and pretraining datasets.](https://github.com/junxia97/awesome-pretrain-on-graphs)\n\n## Citation\n```\n@inproceedings{xia2022progcl,\n  title={ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning},\n  author={Xia, Jun and Wu, Lirong and Wang, Ge and Li, Stan Z.},\n  booktitle={International conference on machine learning},\n  year={2022},\n  organization={PMLR}\n}\n```\n","funding_links":[],"categories":["Self-Supervised Learning"],"sub_categories":["**Contrastive Learning**"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjunxia97%2FProGCL","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjunxia97%2FProGCL","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjunxia97%2FProGCL/lists"}