{"id":16750471,"url":"https://github.com/mberr/ea-active-learning","last_synced_at":"2025-07-11T14:34:51.774Z","repository":{"id":73433647,"uuid":"324987922","full_name":"mberr/ea-active-learning","owner":"mberr","description":"Code for paper \"Active Learning for Entity Alignment\" (https://arxiv.org/abs/2001.08943)","archived":false,"fork":false,"pushed_at":"2023-05-01T14:12:15.000Z","size":83,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-10T14:35:33.829Z","etag":null,"topics":["active-learning","entity-alignment","knowledge-graph"],"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/mberr.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":"2020-12-28T11:00:21.000Z","updated_at":"2024-02-09T09:31:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"1db413fd-3c2b-4925-9247-c602b2fd1b21","html_url":"https://github.com/mberr/ea-active-learning","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/mberr/ea-active-learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mberr%2Fea-active-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mberr%2Fea-active-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mberr%2Fea-active-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mberr%2Fea-active-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mberr","download_url":"https://codeload.github.com/mberr/ea-active-learning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mberr%2Fea-active-learning/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264833284,"owners_count":23670617,"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":["active-learning","entity-alignment","knowledge-graph"],"created_at":"2024-10-13T02:28:15.277Z","updated_at":"2025-07-11T14:34:51.725Z","avatar_url":"https://github.com/mberr.png","language":"Python","readme":"# Active Learning for Entity Alignment\n\n[![Arxiv](https://img.shields.io/badge/arXiv-2001.08943-b31b1b)](https://arxiv.org/abs/2001.08943)\n[![Python 3.8](https://img.shields.io/badge/Python-3.8-2d618c?logo=python)](https://docs.python.org/3.8/)\n[![PyTorch](https://img.shields.io/badge/Made%20with-PyTorch-ee4c2c?logo=pytorch)](https://pytorch.org/docs/stable/index.html)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n\nThis repository contains the source code for the paper\n\n```\nActive Learning for Entity Alignment\nMax Berrendorf*, Evgeniy Faerman*, and Volker Tresp\nhttps://arxiv.org/abs/2001.08943\n```\n\n# Installation\n\nSetup and activate a virtual environment:\n\n```shell script\npython3.8 -m venv ./venv\nsource ./venv/bin/activate\n```\n\nInstall requirements (in this virtual environment):\n\n```shell script\npip install -U pip\npip install -U -r requirements.txt\n```\n\n# Preparation\n\nIn order to track results to a MLFlow server, start it first by running\n\n```shell script\nmlflow server\n```\n\n_Note: When storing the result for many configurations, we recommend to setup a database backend following the [instructions](https://mlflow.org/docs/latest/tracking.html)._\nFor the following examples, we assume that the server is running at\n\n```shell script\nTRACKING_URI=http://localhost:5000\n```\n\n# Experiments\n\nFor all experiments the results are logged to the running MLFlow instance. You can inspect the results during training by accessing the `TRACKING_URI` through a browser.\nMoreover, all experiments are synced via the MLFlow instance.\nThus, you can start multiple instances of each command on different worker machines to parallelize the experiment.\n\n## Random Baseline\n\nTo run the random baseline use\n\n```shell script\nPYTHONPATH=./src python3 executables/evaluate_active_learning_heuristic.py --phase=random --tracking_uri=${TRACKING_URI}\n```\n\n## Hyperparameter Search\n\nTo run the hyperparameter search use\n\n```shell script\nPYTHONPATH=./src python3 executables/evaluate_active_learning_heuristic.py --phase=hpo --tracking_uri=${TRACKING_URI}\n```\n\n_Note: The hyperparameter searches takes a significant amount of time (~multiple days), and requires access to GPU(s). You can abort the script at any time, and inspect the current results via the web interface of MLFlow._\n\n## Best Configurations\n\nTo rerun the best configurations we found in our hyperparameter search use\n\n```shell script\nPYTHONPATH=./src python3 executables/evaluate_active_learning_heuristic.py --phase=best --tracking_uri=${TRACKING_URI}\n```\n\n# Evaluation\n\nTo reproduce the tables and numbers of the paper use\n\n```bash\nPYTHONPATH=./src python3 executables/collate_results.py --tracking_uri=${TRACKING_URI}\n```\n\nTo avoid re-downloading data from a remote MLFLow instance, the metrics and parameters get buffered. To enforce a re-download, e.g., since you conducted additional runs, use `--force`.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmberr%2Fea-active-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmberr%2Fea-active-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmberr%2Fea-active-learning/lists"}