{"id":18802419,"url":"https://github.com/jd-opensource/ia-gcn","last_synced_at":"2026-04-04T12:59:41.913Z","repository":{"id":183889805,"uuid":"670885040","full_name":"jd-opensource/IA-GCN","owner":"jd-opensource","description":null,"archived":false,"fork":false,"pushed_at":"2024-02-16T16:32:33.000Z","size":19359,"stargazers_count":4,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-20T18:41:54.929Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jd-opensource.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":"2023-07-26T04:09:53.000Z","updated_at":"2024-02-13T18:52:32.000Z","dependencies_parsed_at":"2024-11-07T22:31:16.297Z","dependency_job_id":"5e5b6872-c570-464f-acd8-de49a7a961d7","html_url":"https://github.com/jd-opensource/IA-GCN","commit_stats":null,"previous_names":["yinanzhangepfl/ia-gcn","jd-opensource/ia-gcn"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jd-opensource/IA-GCN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-opensource%2FIA-GCN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-opensource%2FIA-GCN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-opensource%2FIA-GCN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-opensource%2FIA-GCN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jd-opensource","download_url":"https://codeload.github.com/jd-opensource/IA-GCN/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-opensource%2FIA-GCN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31400460,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T10:20:44.708Z","status":"ssl_error","status_checked_at":"2026-04-04T10:20:06.846Z","response_time":60,"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":[],"created_at":"2024-11-07T22:28:03.074Z","updated_at":"2026-04-04T12:59:41.895Z","avatar_url":"https://github.com/jd-opensource.png","language":"Python","readme":"# IA-GCN: Interactive Graph Convolutional Network for Recommendation\n\n## Overview\nThis is our Tensorflow implementation for our CIKM 2023 short paper:  \n\u003eZhang, Yinan, et al. \"BI-GCN: Bilateral Interactive Graph Convolutional Network for Recommendation.\" Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2023. (https://dl.acm.org/doi/abs/10.1145/3583780.3615232).\n\nWe also provide a long version on arxiv: IA-GCN: Interactive Graph Convolutional Network for Recommendation (https://arxiv.org/abs/2204.03827).\n\n\n## Introduction \nIn this work, we propose a novel graph attention model named Interactive GCN (IA-GCN), which introduces bilateral interactive guidance into each user-item pair for preference prediction. By this manner, we can obtain target-aware representations, i.e., the information of the target item/user is explicitly encoded in the user/item representation, for more precise matching. \n\n## Requirements\nThe required packages are as follows: \n* numpy (1.15.0) \n* tensorflow (1.12.0)\n\n## Quick Start\n```\ncd electronics/l2_hyper_weights\npython -u /export/App/training_platform/PinoModel/Light_GCN_ops.py --dataset=electronics --regs=[1e-4] --embed_size=64 --layer_size=[64,64] --lr=6.5e-05 --batch_size=1024 --epoch=1000\n```\n\n## Example to run 2-layer IA-GCN\n* For data preprocessing, run make_pkl function located in electronics/l2_hyper_weights/utility/load_data.py to generate 'data_bin'. Note: the parameter layer_num equals 2 in this example but needs to be changed accordingly.\n* for custom op compliation, run following commands to generate the 'tree_out_load_more.so' file, and put it in the main workspace. \n  ```\n  cd ops/l2\n  sh 1.build.sh\n  ```\n* To Train a model, run the following command\n  ```\n  python -u /export/App/training_platform/PinoModel/Light_GCN_ops.py --dataset=electronics --regs=[1e-4] --embed_size=64 --layer_size=[64,64] --lr=6.5e-05 --batch_size=1024 --epoch=1000\n  ```\n  \n## Dataset\nWe use four open datasets: Amazon-Electronics, Gowalla, Yelp2018, Amazon-Book, which vary in domains, scale, and density. We closely follow the same data split strategy as existing GCN- based CF works [1, 2]\n| Dataset | #Users | #Items | #Interactions | Density |\n| :-----| :-----| :----- | :----- | :----- |\n| Amazon-Electronics | 1435 | 1522 | 35931 | 0.01654 |\n| Gowalla | 29528 | 40981 | 1027370 | 0.00084 |\n| Yelp2018 | 31668 | 38048 | 1561406 | 0.00130 |\n| Amazon-Book | 52643 | 91599 | 2984108 | 0.00062 |\n\n## References\n[1] He, Xiangnan, et al. \"Lightgcn: Simplifying and powering graph convolution network for recommendation.\" Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval. 2020.\n\n[2] Mao, Kelong, et al. \"UltraGCN: ultra simplification of graph convolutional networks for recommendation.\" Proceedings of the 30th ACM International Conference on Information \u0026 Knowledge Management. 2021.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjd-opensource%2Fia-gcn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjd-opensource%2Fia-gcn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjd-opensource%2Fia-gcn/lists"}