{"id":17244472,"url":"https://github.com/huangjunjie-cs/sbgnn","last_synced_at":"2025-04-14T04:06:56.393Z","repository":{"id":156973019,"uuid":"394117659","full_name":"huangjunjie-cs/SBGNN","owner":"huangjunjie-cs","description":"source code for signed bipartite graph neural networks(CIKM 2021)","archived":false,"fork":false,"pushed_at":"2022-03-08T14:34:05.000Z","size":4076,"stargazers_count":19,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T17:52:04.719Z","etag":null,"topics":["graph-neural-networks","peer-reviews","product-reviews","signed-graph","vote-prediction"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2108.09638","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/huangjunjie-cs.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-08-09T02:07:20.000Z","updated_at":"2025-03-14T13:21:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"e3885e15-50c8-4183-91ee-05cd44e9f169","html_url":"https://github.com/huangjunjie-cs/SBGNN","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/huangjunjie-cs%2FSBGNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangjunjie-cs%2FSBGNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangjunjie-cs%2FSBGNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangjunjie-cs%2FSBGNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/huangjunjie-cs","download_url":"https://codeload.github.com/huangjunjie-cs/SBGNN/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248819398,"owners_count":21166477,"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":["graph-neural-networks","peer-reviews","product-reviews","signed-graph","vote-prediction"],"created_at":"2024-10-15T06:18:48.630Z","updated_at":"2025-04-14T04:06:56.387Z","avatar_url":"https://github.com/huangjunjie-cs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Signed Bipartite Graph Neural Networks\n\n## This is our PyTorch implementation code for our paper:\n\u003e Signed Bipartite Graph Neural Networks (CIKM2021)\n\u003e \n\u003e [arXiv](https://arxiv.org/abs/2108.09638)\n\n\n## Introduction\n\n\u003cdiv style=\"margin: 20px;\"\u003e\n\u003cimg align='right' src=\"./imgs/SBN.png\" width=\"300\"\u003e\n\n\u003cp\u003e\nFigure shows some common application scenarios for signed bipartite networks, including \u003cstrong\u003eproduct review, bill\nvote, and peer review\u003c/strong\u003e. \n\u003c/p\u003e\n\u003cp\u003eSome opinions can be viewed as positive\nrelationships, such as favorable reviews on products, supporting\nthe bill, accepting a paper, and so on. Meanwhile, some opinions\nare negative links that indicate negative reviews, disapproving a\nbill, rejecting a paper, and so forth. These scenarios can be modeled\nas signed bipartite networks, which include two sets of nodes (i.e.,\nU and V) and the links with positive and negative relationships\nbetween two sets.\n\u003c/p\u003e\n\u003c/div\u003e\n\n\u003cbr/\u003e\n\n## Method\n\n\u003cimg src=\"./imgs/SBGNN-plot.png\" /\u003e\n\u003cdiv style=\"margin: 20px;\"\u003e\n Illustration of SBGNN. SBGNN Layer includes Aggeregate and Update functions. The aggregated message comes from the Set1 and Set2 with positive and negative links. After getting the embedding of the node u_i and v_i, it can be used to predict the link sign relationship.\n\u003c/div\u003e\n\n## Dataset\n\nFor `bonanza, house, senate`, you can download it from this [repository](https://github.com/tylersnetwork/signed_bipartite_networks).\nFor `review` dataset, you can download [it](./experiments-data/review-cikm2021.txt) in ```experiments-data``` folder.\n\n\n## Dependency\nIn order to run this code, you need to install following dependencies:\n\n```\npip install torch numpy sklearn tqdm tensorboard\n```\n\n\n## Run Example\n\n```\npython sbgnn.py --lr 5e-3 --seed 222 \\\n                --dataset_name house1to10-1 --gnn_layer 2 \\\n                --epoch 2000 --agg AttentionAggregator\n```\n\nResults:\n\n```\ntest_auc 0.8498742632577166 \ntest_f1 0.8592910848549948 \ntest_macro_f1 0.848896372204643 \ntest_micro_f1 0.8496114447191806\n```\n\n## Citation\n\nPlease cite our paper if you use this code in your own work\n\n```\n@inproceedings{huang2021signed,\n  title     = {Signed Bipartite Graph Neural Networks},\n  author    = {Huang, Junjie and Shen, Huawei and Cao, Qi and Tao, ShuChang and Cheng, Xueqi},\n  booktitle = {{CIKM} '21: The 30th {ACM} International Conference on Information\n               and Knowledge Management, Virtual Event, Queensland, Australia, November\n               1 - 5, 2021},  \n  year      = {2021},\n  pages     = {740--749},\n  publisher = {{ACM}},\n  year      = {2021},\n  url       = {https://doi.org/10.1145/3459637.3482392},\n  doi       = {10.1145/3459637.3482392},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuangjunjie-cs%2Fsbgnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhuangjunjie-cs%2Fsbgnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuangjunjie-cs%2Fsbgnn/lists"}