{"id":15902149,"url":"https://github.com/younesbelkada/altegrad_challenge","last_synced_at":"2025-04-02T20:11:33.859Z","repository":{"id":96806452,"uuid":"450886060","full_name":"younesbelkada/altegrad_challenge","owner":"younesbelkada","description":"Altegrad 2021-2022 - Citation Prediction Challenge - A complete guide and code to crack the citation prediction altegrad challenge - https://www.kaggle.com/c/altegrad-2021/ - MVA Masters program 2021-2022","archived":false,"fork":false,"pushed_at":"2022-02-24T12:45:29.000Z","size":10308,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-08T10:32:03.428Z","etag":null,"topics":["article","deep-learning","feature-extraction","graph-neural-networks","huggingface-transformers","keybert","link-prediction","sentence-transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/younesbelkada.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":"2022-01-22T17:23:28.000Z","updated_at":"2022-11-28T12:14:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"99f7d2fd-3b9a-4097-8d57-b08c9413eeba","html_url":"https://github.com/younesbelkada/altegrad_challenge","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/younesbelkada%2Faltegrad_challenge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/younesbelkada%2Faltegrad_challenge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/younesbelkada%2Faltegrad_challenge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/younesbelkada%2Faltegrad_challenge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/younesbelkada","download_url":"https://codeload.github.com/younesbelkada/altegrad_challenge/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246884769,"owners_count":20849554,"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":["article","deep-learning","feature-extraction","graph-neural-networks","huggingface-transformers","keybert","link-prediction","sentence-transformers"],"created_at":"2024-10-06T11:22:42.147Z","updated_at":"2025-04-02T20:11:33.829Z","avatar_url":"https://github.com/younesbelkada.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Altegrad 2021-2022 - Citation Prediction Challenge\n\n\u003e Authors: [Apavou Clément](https://github.com/clementapa) \u0026 [Belkada Younes](https://github.com/younesbelkada) \u0026 [Zucker Arthur](https://github.com/ArthurZucker)\n\n![Python](https://img.shields.io/badge/Python-green.svg?style=plastic)\n![PyTorch](https://img.shields.io/badge/PyTorch-orange.svg?style=plastic)\n![PyTorch Lightning](https://img.shields.io/badge/PyTorch-Lightning-blueviolet.svg?style=plastic)\n\nThe kaggle challenge is the following : https://www.kaggle.com/c/altegrad-2021/leaderboard\n## :mag_right: Introduction\n\nIn this challenge, we are given a large scientific citation graph, with each node corresponding to a certain article. The dataset consists of 138 499 vertices i.e articles, with their associated abstract and list of authors. The goal is to be able to predict whether two nodes are citing each other, given all this information. In the next sections, we will try to elaborate on the various intuitions behind our approaches, and present the obtained results as well as some possible interpretations for each observations. The provided code corresponds to the code that we have used for the best model (i.e [the right commit](https://github.com/younesbelkada/altegrad_challenge/tree/best-model) ).\n\n## :hammer: Getting started\n\n```\npip3 install requirements.txt\n```\n\nThen,\n\n```\nsh download_data.sh\n```\n\n```\npython3 main.py\n```\n\n## :round_pushpin: Tips\nThe best model can be used using the [`best-model`](https://github.com/younesbelkada/altegrad_challenge/tree/best-model) branch, as it does not use this implementation of the code. \nThis branch is the final code as it allows customization of the various embeddings and corresponds to the latest version of the code.\n\n## :mag_right: Results\n\n\u003cp align=\"center\"\u003e\n    \n| Model| loss validation |loss test (private leaderboard) | Run  |\n|---|---|---|---|\n| Best model | 0.07775 | 0.07939 | [![](https://github.com/wandb/assets/blob/main/wandb-github-badge-gradient.svg)](https://wandb.ai/altegrad-gnn-link-prediction/test-altegrad/runs/1cwlegzz?workspace=user-clementapa) |\n\u003c/p\u003e\n\nAll experiments are available on wandb: \\\n [![](https://github.com/wandb/assets/blob/main/wandb-github-badge-gradient.svg)](https://wandb.ai/altegrad-gnn-link-prediction/altegrad_challenge?workspace=user-clementapa)\\\n[![](https://github.com/wandb/assets/blob/main/wandb-github-badge-gradient.svg)](https://wandb.ai/altegrad-gnn-link-prediction/test-altegrad?workspace=user-clementapa)\n\n## :diamonds: Best MLP architecture\n\n \u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/younesbelkada/altegrad_challenge/blob/main/assets/MLP_arch.svg\" width=\"100%\" height=\"100%\" alt=\"Architecture\"/\u003e\n\u003c/p\u003e\n\n## :paperclip: Presentation of our work\n\n[Report](https://github.com/younesbelkada/altegrad_challenge/blob/main/assets/Report.pdf) \u0026 [Slides](https://github.com/younesbelkada/altegrad_challenge/blob/main/assets/Slides.pdf)\n\n## :wrench: Some tools used\n \n \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://huggingface.co/sentence-transformers/allenai-specter\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/huggingface/awesome-huggingface/main/logo.svg\" width=\"10%\" height=\"10%\" alt=\"logo hugging face\"/\u003e\n    \u003ca href=\"https://maartengr.github.io/KeyBERT/\"\u003e\n  \u003cimg src=\"https://github.com/MaartenGr/KeyBERT/blob/master/images/logo.png\" width=\"25%\" height=\"25%\" alt=\"logo Keybert\"/\u003e\n\u003c/p\u003e\n\n## Some citations\n\n```bibtex\n@misc{cohan2020specter,\n      title={SPECTER: Document-level Representation Learning using Citation-informed Transformers}, \n      author={Arman Cohan and Sergey Feldman and Iz Beltagy and Doug Downey and Daniel S. Weld},\n      year={2020},\n      eprint={2004.07180},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyounesbelkada%2Faltegrad_challenge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyounesbelkada%2Faltegrad_challenge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyounesbelkada%2Faltegrad_challenge/lists"}