{"id":13628086,"url":"https://github.com/zhengwang100/RECT","last_synced_at":"2025-04-17T00:33:22.687Z","repository":{"id":112529449,"uuid":"242474364","full_name":"zhengwang100/RECT","owner":"zhengwang100","description":"This is the source code of \"Network Embedding with Completely-Imbalanced Labels\". TKDE2020","archived":false,"fork":false,"pushed_at":"2021-03-23T06:05:58.000Z","size":10142,"stargazers_count":18,"open_issues_count":0,"forks_count":7,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-11-08T18:46:12.392Z","etag":null,"topics":["graph-embedding","graph-representation-learning","network-embedding"],"latest_commit_sha":null,"homepage":null,"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/zhengwang100.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}},"created_at":"2020-02-23T07:23:35.000Z","updated_at":"2024-03-25T03:32:45.000Z","dependencies_parsed_at":"2023-06-26T22:25:52.082Z","dependency_job_id":null,"html_url":"https://github.com/zhengwang100/RECT","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/zhengwang100%2FRECT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhengwang100%2FRECT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhengwang100%2FRECT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhengwang100%2FRECT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zhengwang100","download_url":"https://codeload.github.com/zhengwang100/RECT/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":["graph-embedding","graph-representation-learning","network-embedding"],"created_at":"2024-08-01T22:00:44.954Z","updated_at":"2025-04-17T00:33:21.994Z","avatar_url":"https://github.com/zhengwang100.png","language":"Python","funding_links":[],"categories":["Uncategorized"],"sub_categories":["Uncategorized"],"readme":"# RECT (python source code)\r\nNetwork Embedding with Completely-imbalanced Labels. TKDE2020 [paper](https://zhengwang100.github.io/pdf/TKDE20_wzheng.pdf).\r\nThis is a deep method for the problem of [Zero-shot Graph Embedding (ZGE)](https://zhengwang100.github.io/project/zero_shot_graph_embedding.html), i.e., graph embeddings when labeled data cannot cover all classes. \r\n\r\nBreifly, RECT contains two parts:\r\n---\r\n- RECT-L is the supervised part in which a semantic loss is used. \r\n- RECT-N is the unsupervised part in which the network structure is preserved. Note, this part can be replaced by any unsupervised NRL methods.\r\n\r\n\r\nUsage (abstract):\r\n---\r\n- set the dataset \r\n- python main_rect.py\r\n\r\n```\r\n------ evaluate RECT-N ---------\r\nTraining an SVM classifier under the pre-defined split setting...\r\n(0.7335058214747736, 0.670830503861163)\r\n------ evaluate RECT-L ---------\r\nTraining an SVM classifier under the pre-defined split setting...\r\n(0.7141871496334627, 0.6402691559469643)\r\n------ evaluate RECT ---------\r\nTraining an SVM classifier under the pre-defined split setting...\r\n(0.7441138421733506, 0.6805281849343917)\r\n```\r\n\r\n\r\nCiting\r\n---\r\nIf you find this useful in your research, please cit our paper, thx:\r\n```\r\n@article{wang2020RECT,\r\n  title={Network Embedding with Completely-imbalanced Labels},\r\n  author={Wang, Zheng and Ye, Xiaojun and Wang, Chaokun and Cui, Jian and Yu, Philip S},\r\n  journal={TKDE},\r\n  year={2020},\r\n  doi = {10.1109/TKDE.2020.2971490},\r\n  publisher={IEEE}\r\n}\r\n```\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhengwang100%2FRECT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzhengwang100%2FRECT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhengwang100%2FRECT/lists"}