{"id":13628210,"url":"https://github.com/ibalazevic/TuckER","last_synced_at":"2025-04-17T00:33:59.631Z","repository":{"id":75535345,"uuid":"167696782","full_name":"ibalazevic/TuckER","owner":"ibalazevic","description":"TuckER: Tensor Factorization for Knowledge Graph Completion","archived":false,"fork":false,"pushed_at":"2023-11-16T15:14:14.000Z","size":13765,"stargazers_count":351,"open_issues_count":2,"forks_count":60,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-08-01T22:42:03.807Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ibalazevic.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":"2019-01-26T14:18:02.000Z","updated_at":"2024-07-24T10:16:36.000Z","dependencies_parsed_at":"2024-08-01T22:51:48.025Z","dependency_job_id":null,"html_url":"https://github.com/ibalazevic/TuckER","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/ibalazevic%2FTuckER","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibalazevic%2FTuckER/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibalazevic%2FTuckER/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibalazevic%2FTuckER/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ibalazevic","download_url":"https://codeload.github.com/ibalazevic/TuckER/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223735372,"owners_count":17194090,"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":"2024-08-01T22:00:48.395Z","updated_at":"2024-11-08T18:31:40.009Z","avatar_url":"https://github.com/ibalazevic.png","language":"Python","funding_links":[],"categories":["Uncategorized","Paper implementations｜论文实现","Paper implementations","Python"],"sub_categories":["Uncategorized","Other libraries｜其他库:","Other libraries:"],"readme":"\n## TuckER: Tensor Factorization for Knowledge Graph Completion\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/ibalazevic/TuckER/master/tucker.png\"/ width=400\u003e\n\u003c/p\u003e\n\nThis codebase contains PyTorch implementation of the paper:\n\n\u003e TuckER: Tensor Factorization for Knowledge Graph Completion.\n\u003e Ivana Balažević, Carl Allen, and Timothy M. Hospedales.\n\u003e Empirical Methods in Natural Language Processing (EMNLP), 2019.\n\u003e [[Paper]](https://arxiv.org/pdf/1901.09590.pdf)\n\n\u003e TuckER: Tensor Factorization for Knowledge Graph Completion.\n\u003e Ivana Balažević, Carl Allen, and Timothy M. Hospedales.\n\u003e ICML Adaptive \u0026 Multitask Learning Workshop, 2019.\n\u003e [[Short Paper]](https://openreview.net/pdf?id=BkgREcHjnE)\n\n### Link Prediction Results\n\nDataset | MRR | Hits@10 | Hits@3 | Hits@1\n:--- | :---: | :---: | :---: | :---:\nFB15k | 0.795 | 0.892 | 0.833 | 0.741\nWN18 | 0.953 | 0.958 | 0.955 | 0.949\nFB15k-237 | 0.358 | 0.544 | 0.394 | 0.266\nWN18RR | 0.470 | 0.526 | 0.482 | 0.443\n\n### Running a model\n\nTo run the model, execute the following command:\n\n     CUDA_VISIBLE_DEVICES=0 python main.py --dataset FB15k-237 --num_iterations 500 --batch_size 128\n                                           --lr 0.0005 --dr 1.0 --edim 200 --rdim 200 --input_dropout 0.3 \n                                           --hidden_dropout1 0.4 --hidden_dropout2 0.5 --label_smoothing 0.1\n\nAvailable datasets are:\n    \n    FB15k-237\n    WN18RR\n    FB15k\n    WN18\n    \nTo reproduce the results from the paper, use the following combinations of hyperparameters with `batch_size=128`:\n\ndataset | lr | dr | edim | rdim | input_d | hidden_d1 | hidden_d2 | label_smoothing \n:--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:\nFB15k | 0.003 | 0.99 | 200 | 200 | 0.2 | 0.2 | 0.3 | 0.\nWN18 | 0.005 | 0.995 | 200 | 30 | 0.2 | 0.1 | 0.2 | 0.1\nFB15k-237 | 0.0005 | 1.0 | 200 | 200 | 0.3 | 0.4 | 0.5 | 0.1\nWN18RR | 0.003 | 1.0 | 200 | 30 | 0.2 | 0.2 | 0.3| 0.1\n    \n### Requirements\n\nThe codebase is implemented in Python 3.6.6. Required packages are:\n\n    numpy      1.15.1\n    pytorch    1.0.1\n    \n### Citation\n\nIf you found this codebase useful, please cite:\n\n    @inproceedings{balazevic2019tucker,\n    title={TuckER: Tensor Factorization for Knowledge Graph Completion},\n    author={Bala\\v{z}evi\\'c, Ivana and Allen, Carl and Hospedales, Timothy M},\n    booktitle={Empirical Methods in Natural Language Processing},\n    year={2019}\n    }\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fibalazevic%2FTuckER","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fibalazevic%2FTuckER","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fibalazevic%2FTuckER/lists"}