{"id":21258240,"url":"https://github.com/aida-ugent/nrl4lp","last_synced_at":"2025-08-30T18:12:57.045Z","repository":{"id":50739044,"uuid":"300561074","full_name":"aida-ugent/NRL4LP","owner":"aida-ugent","description":"Instructions for replicating the experiments in the paper \"Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?\" (DSAA2020)","archived":false,"fork":false,"pushed_at":"2021-05-10T19:02:29.000Z","size":135,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-21T21:33:40.255Z","etag":null,"topics":["benchmark","evaluation","link-prediction","network-embedding","representation-learning"],"latest_commit_sha":null,"homepage":"https://ieeexplore.ieee.org/document/9260030","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/aida-ugent.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}},"created_at":"2020-10-02T09:11:17.000Z","updated_at":"2022-08-01T06:57:56.000Z","dependencies_parsed_at":"2022-09-02T18:41:36.795Z","dependency_job_id":null,"html_url":"https://github.com/aida-ugent/NRL4LP","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/aida-ugent%2FNRL4LP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aida-ugent%2FNRL4LP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aida-ugent%2FNRL4LP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aida-ugent%2FNRL4LP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aida-ugent","download_url":"https://codeload.github.com/aida-ugent/NRL4LP/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243691431,"owners_count":20331969,"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":["benchmark","evaluation","link-prediction","network-embedding","representation-learning"],"created_at":"2024-11-21T04:07:51.776Z","updated_at":"2025-03-15T06:24:18.960Z","avatar_url":"https://github.com/aida-ugent.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?\n\nThis repository contains the instructions and materials necessary for reproducing the experiments presented in the \npaper: *Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?*\n\nThe repository is maintained by Alexandru Mara (alexandru.mara@ugent.be).\n\n## Reproducing Experiments\nIn order to reproduce the experiments presented in the paper the following steps are necessary:\n\n1. Download and install the EvalNE library v0.3.2 as instructed by the authors [here](https://github.com/Dru-Mara/EvalNE)\n2. Download and install the implementations of the baseline methods reported in the \n[manuscript](https://arxiv.org/abs/2002.11522). \nWe recommend that each method is installed in a unique virtual environment to ensure that the right \ndependencies are used. \n3. Download the datasets used in the experiments: \n\n    * [StudentDB](http://adrem.ua.ac.be/smurfig)\n    * [Facebook](https://snap.stanford.edu/data/egonets-Facebook.html)\n    * [BlogCatalog](http://socialcomputing.asu.edu/datasets/BlogCatalog3) \n    * [Flickr](http://socialcomputing.asu.edu/datasets/Flickr)\n    * [YouTube](http://socialcomputing.asu.edu/datasets/YouTube2)\n    * [GR-QC](https://snap.stanford.edu/data/ca-GrQc.html)\n    * [DBLP](https://snap.stanford.edu/data/com-DBLP.html)\n    * [PPI](http://snap.stanford.edu/node2vec/#datasets)\n    * [Wikipedia](http://snap.stanford.edu/node2vec/#datasets)\n\n4. Modify the `.ini` configuration files from this folder to match the paths where the *datasets* are\nstored on your system as well as the paths where the *methods* are installed. Run the evaluation as:\n\n    ```bash\n    python -m evalne ./experiments/expLP1.ini\n    ```\n\n**NOTE:** In order to obtain the results for, e.g. different values of the embedding dimensionality, the \nconf file `expLP1.ini` has to be modified accordingly and the previous command rerun.\n\n**NOTE:** For AROPE, VERSE and the GEM library, special `main.py` files are required in order to run the \nevaluation through EvalNE. Once these methods are installed, the corresponding main file has to be added \nto the root folder of the method and called from the `.ini` configuration file. These `main.py` files are \nlocated in a `main_files` folder.\n\n\n## Citation ##\nIf you have found our research useful, please consider citing our \n[paper](https://ieeexplore.ieee.org/document/9260030), which is also available on [arxiv](https://arxiv.org/abs/2002.11522):\n\n```bibtex\n@INPROCEEDINGS{9260030,\n  author={A. C. {Mara} and J. {Lijffijt} and T. d. {Bie}},\n  booktitle={2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA)}, \n  title={Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?}, \n  year={2020},\n  pages={138-147},\n  doi={10.1109/DSAA49011.2020.00026}}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faida-ugent%2Fnrl4lp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faida-ugent%2Fnrl4lp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faida-ugent%2Fnrl4lp/lists"}