{"id":13810801,"url":"https://github.com/HKUST-KnowComp/GeoAlign","last_synced_at":"2025-05-14T15:31:19.897Z","repository":{"id":101128861,"uuid":"407049057","full_name":"HKUST-KnowComp/GeoAlign","owner":"HKUST-KnowComp","description":"Source code for AKBC 2021 paper \"Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning\"","archived":false,"fork":false,"pushed_at":"2021-10-24T16:55:41.000Z","size":38371,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-19T05:55:40.552Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/HKUST-KnowComp.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}},"created_at":"2021-09-16T06:31:27.000Z","updated_at":"2022-03-10T14:43:29.000Z","dependencies_parsed_at":"2023-05-24T17:00:12.232Z","dependency_job_id":null,"html_url":"https://github.com/HKUST-KnowComp/GeoAlign","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/HKUST-KnowComp%2FGeoAlign","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HKUST-KnowComp%2FGeoAlign/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HKUST-KnowComp%2FGeoAlign/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HKUST-KnowComp%2FGeoAlign/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HKUST-KnowComp","download_url":"https://codeload.github.com/HKUST-KnowComp/GeoAlign/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254171779,"owners_count":22026517,"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":"2024-08-04T03:00:26.762Z","updated_at":"2025-05-14T15:31:14.878Z","avatar_url":"https://github.com/HKUST-KnowComp.png","language":"Python","funding_links":[],"categories":["Taxonomy Applications"],"sub_categories":["Help Text Understanding and Representation Learning"],"readme":"# GeoAlign\nSource code for AKBC 2021 paper [Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning](https://www.akbc.ws/2021/assets/pdfs/TPymTKJR-Pi.pdf).\n\n### Requirements\n* python: 3.6\n* torch: 1.0.0\n* scikit-learn\n* pandas\n* cython\n* tqdm\n* numpy\n\nThe hyperbolic embeddings in this repository (the poincare-embeddings folder) is inherited from the [poincare-embeddings repository](https://github.com/facebookresearch/poincare-embeddings).\n\n## Data\nWe construct two taxonomies (YAGOwordnet and wikiObjects) and one knowledge graph (YAGOfacts) from [YAGO3](https://yago-knowledge.org/downloads/yago-3). Please refer to our paper for the data construction details.\n\n#### Taxonomy data\n* taxonomy.csv: This file contains the edges (i.e., the hypernymy relations) of the taxonomy.\n* full_taxonomy.csv: This file contains the edges of the full transitive closure of the taxonomy, which is used in our experiments.\n* full_transitive.txt / basic_edges.txt: The edges in the full transitive closure of the taxonomy / the transitive reduction of the taxonomy.\n* types.txt / entities.txt / taxonomy_nodes.txt: The types / entities / union of types and entities in the taxonomy.\n* taxonomy: The folder contains the training set and test set under different training rates.\n\n#### Knowledge graph data\n* TransE_KG: The folder contains the pretrained TransE embeddings of YAGOfacts named 'TransE.ckpt'. Please obtain a pairwise distance matrix of the entity embeddings and store it in this folder before running the code.\n\n## Usage\nTo run the whole framework, run:\n```\nzsh run_all.sh\n```\nor\n```\necho $Training_Rate\"\\n\"$Data\"\\n\"$Dimension\"\\n\"$Hyperbolic_Model\"\\n\" | xargs -L 4 -P $PARALLEL_R bash hyper_label_rate.sh\n```\nwhere $Training_Rate = {1, 2, 3, 4, 5}; $Data = {YAGOwordnet, wikiObjects}; $Dimension is the embedding dimension of the hyperbolic space; $Hyperbolic_Model = {lorentz, poincare}; $PARALLEL_R is the number of parallel programs.\nMore parameters can be edited in constants.sh.\n\n### Citation\nIf you find this repository useful for your research, please kindly cite our paper:\n```angular2\n@inproceedings{\nxiao2021manifold,\ntitle={Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning},\nauthor={Huiru Xiao and Yangqiu Song},\nbooktitle={3rd Conference on Automated Knowledge Base Construction},\nyear={2021},\nurl={https://openreview.net/forum?id=TPymTKJR-Pi}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHKUST-KnowComp%2FGeoAlign","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FHKUST-KnowComp%2FGeoAlign","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHKUST-KnowComp%2FGeoAlign/lists"}