{"id":29650571,"url":"https://github.com/EdisonLeeeee/SpikeGCL","last_synced_at":"2025-07-22T05:02:24.952Z","repository":{"id":164655230,"uuid":"640100529","full_name":"EdisonLeeeee/SpikeGCL","owner":"EdisonLeeeee","description":"[ICLR 2024] Official implementation of Spiking Graph Contrastive Learning (0️⃣1️⃣ SpikeGCL)","archived":false,"fork":false,"pushed_at":"2024-05-08T07:11:42.000Z","size":930,"stargazers_count":30,"open_issues_count":1,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-05-04T04:33:23.363Z","etag":null,"topics":["graph-contrastive-learning","graph-neural-networks","iclr","spiking-neural-networks"],"latest_commit_sha":null,"homepage":"https://openreview.net/forum?id=LnLySuf1vp","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/EdisonLeeeee.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-05-13T02:07:01.000Z","updated_at":"2025-02-13T16:43:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"992326d2-0c49-40c6-869e-8dc0c47d9d38","html_url":"https://github.com/EdisonLeeeee/SpikeGCL","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/EdisonLeeeee/SpikeGCL","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdisonLeeeee%2FSpikeGCL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdisonLeeeee%2FSpikeGCL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdisonLeeeee%2FSpikeGCL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdisonLeeeee%2FSpikeGCL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EdisonLeeeee","download_url":"https://codeload.github.com/EdisonLeeeee/SpikeGCL/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdisonLeeeee%2FSpikeGCL/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266430671,"owners_count":23927165,"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","status":"online","status_checked_at":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"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":["graph-contrastive-learning","graph-neural-networks","iclr","spiking-neural-networks"],"created_at":"2025-07-22T05:01:28.821Z","updated_at":"2025-07-22T05:02:24.924Z","avatar_url":"https://github.com/EdisonLeeeee.png","language":"Python","funding_links":[],"categories":["Applications"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ch1\u003e0️⃣1️⃣ SpikeGCL (Spiking Graph Contrastive Learning)\u003c/h1\u003e\n\u003ch3\u003eA Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks\u003c/h3\u003e\n\nJintang Li\u003csup\u003e1\u003c/sup\u003e, Huizhe Zhang\u003csup\u003e1\u003c/sup\u003e, Ruofan Wu\u003csup\u003e2\u003c/sup\u003e, Zulun Zhu\u003csup\u003e3\u003c/sup\u003e, Baokun Wang\u003csup\u003e2\u003c/sup\u003e, Changhua Meng\u003csup\u003e2\u003c/sup\u003e, Zibin Zheng\u003csup\u003e1\u003c/sup\u003e, Liang Chen\u003csup\u003e1\u003c/sup\u003e\n\n\u003csup\u003e1\u003c/sup\u003eSun Yat-sen University, \u003csup\u003e2\u003c/sup\u003eAnt Group, \u003csup\u003e3\u003c/sup\u003eNanyang Technological University\n \n\narXiv ([arXiv:2305.19306](https://arxiv.org/abs/2305.19306)),\nOpenReview ([ICLR'24](https://openreview.net/forum?id=LnLySuf1vp))\n\n[Poster](https://iclr.cc/media/PosterPDFs/ICLR%202024/18850.png?t=1713083679.2213657) | [Slides](https://iclr.cc/media/iclr-2024/Slides/18850.pdf)\n\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg width=\"504\" src=\"imgs/comparison.png\"/\u003e\n\u003c/div\u003e\n\n\n## Environments\n\n\u003e [!NOTE]\n\u003e Higher versions should be also compatible.\n\n+ numpy == 1.23.3\n+ torch == 1.8+cu111\n+ torch-cluster == 1.6.1\n+ torch_geometric == 2.3.0\n+ torch-scatter == 2.1.1\n+ torch-sparse == 0.6.17\n+ CUDA 11.1\n+ cuDNN 8.0.5\n\n## Model and Results\n\nSpikeGCL adopts a simple GCL architecture and is comprised of a set of peer GNN encoders and a spiking neuron.\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"imgs/spikegcl.png\"/\u003e\n\u003c/div\u003e\n\nThe following tables present the performance \u0026 efficiency results for standard node classification tasks on several graph benchmark datasets.\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"imgs/tab1.png\"/\u003e\n  \u003cimg src=\"imgs/tab2.png\"/\u003e\n\u003c/div\u003e\n\n## Reproduction\n\n+ Cora\n```\npython main.py --dataset Cora --threshold 5e-4 --outs 2 --T 64 --bn --epochs 5\n```\n+ Citeseer\n```\npython main.py --dataset Citeseer --threshold 5e-3 --T 32 --bn --epochs 5\n```\n+ Pubmed\n```\npython main.py --dataset Pubmed --threshold 5e-2 --bn --T 32 --epochs 50\n```\n+ Computers\n```\npython main.py --dataset Computers --threshold 5e-2 --outs 32 --bn --T 25\n```\n+ Photo \n```\npython main.py --dataset Photo --threshold 5e-2 --T 15 --bn --outs 8 --epochs 50\n```\n+ CS\n```\npython main.py --dataset CS --threshold 5e-1 --outs 32 --T 60 --dropout 0. --bn\n```\n+ Physics \n```\npython main.py --dataset Physics --T 25 --outs 16 --margin 1 --threshold 5e-2 --bn\n```\n+ Ogbn-arXiv\n```\npython main.py --dataset ogbn-arxiv --T 30 --outs 1 --threshold 5e-2 --no_shuffle --bn --dropout 0.\n```\n+ Ogbn-MAG\n```\npython main.py --dataset ogbn-mag --T 8 --outs 8 --hids 64 --threshold 5e-3 --no_shuffle --bn\n```\n\n## Citation\nIf you find this repository useful in your research, please consider giving a star ⭐ and a citation\n\n```bibtex\n@inproceedings{spikegcl,\n    title={A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks},\n    author={Jintang Li and Huizhe Zhang and Ruofan Wu and Zulun Zhu and Baokun Wang and Changhua Meng and Zibin Zheng and Liang Chen},\n    booktitle={ICLR},\n    year={2024},\n    url={https://openreview.net/forum?id=LnLySuf1vp}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEdisonLeeeee%2FSpikeGCL","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEdisonLeeeee%2FSpikeGCL","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEdisonLeeeee%2FSpikeGCL/lists"}