{"id":13788754,"url":"https://github.com/divelab/lgcn","last_synced_at":"2025-04-27T19:32:26.761Z","repository":{"id":44909287,"uuid":"120689574","full_name":"divelab/lgcn","owner":"divelab","description":null,"archived":false,"fork":false,"pushed_at":"2020-06-16T21:17:39.000Z","size":453,"stargazers_count":136,"open_issues_count":4,"forks_count":65,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-25T07:02:27.594Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/divelab.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}},"created_at":"2018-02-08T00:28:50.000Z","updated_at":"2024-05-22T20:09:48.000Z","dependencies_parsed_at":"2022-08-26T08:01:38.754Z","dependency_job_id":null,"html_url":"https://github.com/divelab/lgcn","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/divelab%2Flgcn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2Flgcn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2Flgcn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2Flgcn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/divelab","download_url":"https://codeload.github.com/divelab/lgcn/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251195908,"owners_count":21550866,"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":[],"created_at":"2024-08-03T21:00:52.951Z","updated_at":"2025-04-27T19:32:26.318Z","avatar_url":"https://github.com/divelab.png","language":"Python","funding_links":[],"categories":["TensorFlow Implementations"],"sub_categories":[],"readme":"# Large-Scale Learnable Graph Convolutional Networks(LGCN)\n\nCreated by [Hongyang Gao](http://people.tamu.edu/~hongyang.gao/), [Zhengyang Wang](http://people.tamu.edu/~zhengyang.wang/) and [Shuiwang Ji](http://people.tamu.edu/~sji/) at Texas A\u0026M University.\n\nAccepted by KDD18.\n\n## Introduction\n\nLarge-Scale Learnable Graph Convolutional Networks provide an efficient way (LGCL and LGCN) for learnable graph convolution.\n\nDetailed information about LGCL and LGCN is provided in (https://dl.acm.org/citation.cfm?id=3219947).\n\n## Methods\n\nIn this work, we propose the learnable graph convolution layer\n(LGCL). Based on LGCL. We propose the learnable graph\nconvolutional networks.\n\n### Learnable Graph Convolution Layer\n\n![lgcl](./doc/layer.png)\n\n### Learnable graph Convolutional Networks\n\n![lgcn](./doc/model.png)\n\n### Batch Training\n\n![batch](./doc/batch.png)\n\n## Citation\n\nIf using this code, please cite our paper.\n\n```\n@inproceedings{gao2018large,\n  title={Large-Scale Learnable Graph Convolutional Networks},\n  author={Gao, Hongyang and Wang, Zhengyang and Ji, Shuiwang},\n  booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery \\\u0026 Data Mining},\n  pages={1416--1424},\n  year={2018},\n  organization={ACM}\n}\n```\n\n## Start training\n\nAfter configure the network, we can start to train. Run\n```\npython main.py\n```\nThe training results on Cora dataset will be displayed.\n\n\n## Results\n\n| Models    | Cora  | Citeseer | Pubmed |\n|-----------|-------|----------|--------|\n| DeepWalk  | 67.2% | 43.2%    | 65.3%  |\n| Planetoid | 75.7% | 64.7%    | 77.2%  |\n| Chebyshev | 81.2% | 69.8%    | 74.4%  |\n| GCN       | 81.5% | 70.3%    | 79.0%  |\n| LGCN      |83.3 ± 0.5% | 73.0 ± 0.6% | 79.5 ± 0.2% |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivelab%2Flgcn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdivelab%2Flgcn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivelab%2Flgcn/lists"}