{"id":13628073,"url":"https://github.com/librahu/HeGAN","last_synced_at":"2025-04-17T00:33:27.841Z","repository":{"id":113398564,"uuid":"170280340","full_name":"librahu/HeGAN","owner":"librahu","description":"Source code for KDD 2019 paper \"Adversarial Learning on Heterogeneous Information Networks\"","archived":false,"fork":false,"pushed_at":"2019-05-05T09:34:38.000Z","size":14876,"stargazers_count":70,"open_issues_count":8,"forks_count":25,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-08T18:46:13.962Z","etag":null,"topics":[],"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/librahu.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}},"created_at":"2019-02-12T08:25:30.000Z","updated_at":"2024-10-23T13:18:06.000Z","dependencies_parsed_at":"2023-05-02T13:46:55.777Z","dependency_job_id":null,"html_url":"https://github.com/librahu/HeGAN","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/librahu%2FHeGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librahu%2FHeGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librahu%2FHeGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librahu%2FHeGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/librahu","download_url":"https://codeload.github.com/librahu/HeGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249293184,"owners_count":21245694,"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":"2024-08-01T22:00:44.505Z","updated_at":"2025-04-17T00:33:24.582Z","avatar_url":"https://github.com/librahu.png","language":"Python","funding_links":[],"categories":["Uncategorized"],"sub_categories":["Uncategorized"],"readme":"# HeGAN\nSource code for paper \"Adversarial Learning on Heterogeneous Information Network (KDD2019)\"\n\n## Evironment Setting\n\n* Python == 2.7.3\n\n* Tensorflow == 1.12.0\n\n* Numpy == 1.15.1\n\n## Parameter Setting (see config.py)\nbatch_size : The size of batch.\n\nlambda_gen, lambda_dis : The regularization for generator and discriminator, respectively.\n\nlr_gen, lr_dis : The learning rate for generator and discriminator, respectively.\n\nn_epoch : The maximum training epoch.\n\nsig : The variance of gaussian distribution in generator. \n\ng_epoch, d_epoch: The number of generator and discriminator training per epoch.\n\nn_sample : The size of sample\n\nn_emb : The embedding size\n\n## Files in the folder\n\n* data/: The training data\n\n* results/: The learned embeddings of generator ane discriminator.\n\n* code/: The source codes\n\n* pre_train/: The pre-trained node embeddings (Note: The dimension of pre-trained node embeddings should equal n_emb)\n\n## Data \nWe provide three datasets: [DBLP](https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/tree/master/DBLP), [Yelp](https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/tree/master/Yelp_2) and [Aminer](https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/tree/master/Aminer), The detailed description of the three datasets can refer to https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding\n\n### The format of input training data\n* Each line: source_node target_node relation\n\n### The format of input pre-trained data\n* The first line: node_num embedding_dim\n\n* Each line : node_id embdeeing_1 embedding_2, ...\n\n### The format of output embedding\n* The first line: node_num embedding_dim\n\n* Each line : node_id embdeeing_1 embedding_2, ...\n\n\n## Basic Usage \n\ncd code\n\npython he_gan.py\n\n\n# Reference\n\n@inproceedings{\n\n\u003e author = {Binbin Hu, Yuan Fang and Chuan Shi.},\n \n\u003e title = {Adversarial Learning on Heterogeneous Information Network},\n \n\u003e booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},\n \n\u003e year = {2019},\n \n\u003e publisher = {ACM},\n\n\u003e address = {Anchorage, Alaska, USA},\n\n\u003e year = {2019},\n\n\u003e keywords = {Heterogeneous Information Network, Network Embedding, Generative Adversarial Network},\n \n}\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flibrahu%2FHeGAN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flibrahu%2FHeGAN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flibrahu%2FHeGAN/lists"}