{"id":20515410,"url":"https://github.com/snap-research/nodedup","last_synced_at":"2025-07-21T07:01:55.616Z","repository":{"id":245209988,"uuid":"700514262","full_name":"snap-research/NodeDup","owner":"snap-research","description":"Node Duplication Improves Cold-start Link Prediction","archived":false,"fork":false,"pushed_at":"2024-06-20T01:56:06.000Z","size":76,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-03-05T23:22:20.129Z","etag":null,"topics":["cold-start","data-augmentation","data-augmentation-strategies","gnn","gnns","graph","graphml","link-prediction","ml","recommendation-system","recommender-system"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/snap-research.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":"2023-10-04T18:27:28.000Z","updated_at":"2024-10-24T09:28:08.000Z","dependencies_parsed_at":"2024-06-20T15:10:40.522Z","dependency_job_id":null,"html_url":"https://github.com/snap-research/NodeDup","commit_stats":null,"previous_names":["snap-research/nodedup"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/snap-research/NodeDup","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2FNodeDup","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2FNodeDup/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2FNodeDup/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2FNodeDup/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/snap-research","download_url":"https://codeload.github.com/snap-research/NodeDup/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2FNodeDup/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266255243,"owners_count":23900097,"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":["cold-start","data-augmentation","data-augmentation-strategies","gnn","gnns","graph","graphml","link-prediction","ml","recommendation-system","recommender-system"],"created_at":"2024-11-15T21:21:34.767Z","updated_at":"2025-07-21T07:01:55.598Z","avatar_url":"https://github.com/snap-research.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Node Duplication Improves Cold-start Link Prediction\n\n## Introduction\nThis repository contains the source code for the paper: [Node Duplication Improves Cold-start Link Prediction](https://arxiv.org/pdf/2402.09711) \n\n## Requirements\nThe code was developed and tested with Python 3.10.9. The enviromental requirements are listed as in `requirements.txt`. Please run the following code to install all the requirements:\n```\npip install -r requirements.txt\n```\n\n## Prepare the datasets\nIGB-100K dataset needs to be pre-downloaded and pre-processed. Please install IGB package and download IGB-100k datset as follows:\n```\ngit clone https://github.com/IllinoisGraphBenchmark/IGB-Datasets.git\ncd IGB-Datasets/\npip install .\ncd IGB-Datasets\npython\nfrom igb import dataloader\nfrom igb import download\ndownload.download_dataset(path='../IGB-Datasets', dataset_type='homogeneous', dataset_size='tiny')\n```\nThen pre-process IGB-100K datasets with the following command:\n```\ncd data\npython igb_process.py\n```\nOther datasets can be directly downloaded when running the experimental code. \n\n### Usage\n\n#### Transductive Setting\nPlease run the following command to reproduce the results in Table 1:\n```\nbash scripts/transductive.sh\n```\n\n#### Production Setting\nPlease run the following command to reproduce the results in Table 2 and Table 7 in the paper:\n```\nbash scripts/inductive.sh\n```\n## Citation\nIf you use this code in your research, please cite the following paper:\n\n```bibtex\n@article{guo2024node,\n  title={Node Duplication Improves Cold-start Link Prediction},\n  author={Guo, Zhichun and Zhao, Tong and Liu, Yozen and Dong, Kaiwen and Shiao, William and Shah, Neil and Chawla, Nitesh V},\n  journal={arXiv preprint arXiv:2402.09711},\n  year={2024}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnap-research%2Fnodedup","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsnap-research%2Fnodedup","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnap-research%2Fnodedup/lists"}