{"id":13958297,"url":"https://github.com/kang205/SASRec","last_synced_at":"2025-07-20T23:31:12.201Z","repository":{"id":39717880,"uuid":"148589591","full_name":"kang205/SASRec","owner":"kang205","description":"SASRec: Self-Attentive Sequential Recommendation","archived":false,"fork":false,"pushed_at":"2023-08-21T15:49:17.000Z","size":17643,"stargazers_count":705,"open_issues_count":12,"forks_count":150,"subscribers_count":16,"default_branch":"master","last_synced_at":"2024-08-09T13:18:26.287Z","etag":null,"topics":["deep-learning","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kang205.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}},"created_at":"2018-09-13T06:03:03.000Z","updated_at":"2024-08-07T03:31:08.000Z","dependencies_parsed_at":"2022-07-20T13:32:24.444Z","dependency_job_id":null,"html_url":"https://github.com/kang205/SASRec","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/kang205%2FSASRec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kang205%2FSASRec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kang205%2FSASRec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kang205%2FSASRec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kang205","download_url":"https://codeload.github.com/kang205/SASRec/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226844978,"owners_count":17691137,"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":["deep-learning","recommender-system"],"created_at":"2024-08-08T13:01:28.977Z","updated_at":"2024-11-28T01:31:42.928Z","avatar_url":"https://github.com/kang205.png","language":"Python","funding_links":[],"categories":["其他_推荐系统"],"sub_categories":["网络服务_其他"],"readme":"# SASRec: Self-Attentive Sequential Recommendation\n\nThis is our TensorFlow implementation for the paper:\n\n[Wang-Cheng Kang](http://kwc-oliver.com), [Julian McAuley](http://cseweb.ucsd.edu/~jmcauley/) (2018). *[Self-Attentive Sequential Recommendation.](https://cseweb.ucsd.edu/~jmcauley/pdfs/icdm18.pdf)* In Proceedings of IEEE International Conference on Data Mining (ICDM'18)\n\nPlease cite our paper if you use the code or datasets.\n\nThe code is tested under a Linux desktop (w/ GTX 1080 Ti GPU) with TensorFlow 1.12 and Python 2.\n\nRefer to *[here](https://github.com/pmixer/SASRec.pytorch)* for PyTorch implementation (thanks to pmixer).\n\n## Datasets\n\nThe preprocessed datasets are included in the repo (`e.g. data/Video.txt`), where each line contains an `user id` and \n`item id` (starting from 1) meaning an interaction (sorted by timestamp).\n\nThe data pre-processing script is also included. For example, you could download Amazon review data from *[here.](http://jmcauley.ucsd.edu/data/amazon/index.html)*, and run the script to produce the `txt` format data.\n\n### Steam Dataset\n\nWe crawled reviews and game information from Steam. The dataset contains 7,793,069 reviews, 2,567,538 users, and 32,135 games. In addition to the review text, the data also includes the users' play hours in each review.     \n\n* Download: [reviews (1.3G)](http://cseweb.ucsd.edu/~wckang/steam_reviews.json.gz), [game info (2.7M)](http://cseweb.ucsd.edu/~wckang/steam_games.json.gz)\n* Example (game info):\n```json\n{\n    \"app_name\": \"Portal 2\", \n    \"developer\": \"Valve\", \n    \"early_access\": false, \n    \"genres\": [\"Action\", \"Adventure\"], \n    \"id\": \"620\", \n    \"metascore\": 95, \n    \"price\": 19.99, \n    \"publisher\": \"Valve\", \n    \"release_date\": \"2011-04-18\", \n    \"reviews_url\": \"http://steamcommunity.com/app/620/reviews/?browsefilter=mostrecent\u0026p=1\", \n    \"sentiment\": \"Overwhelmingly Positive\", \n    \"specs\": [\"Single-player\", \"Co-op\", \"Steam Achievements\", \"Full controller support\", \"Steam Trading Cards\", \"Captions available\", \"Steam Workshop\", \"Steam Cloud\", \"Stats\", \"Includes level editor\", \"Commentary available\"], \n    \"tags\": [\"Puzzle\", \"Co-op\", \"First-Person\", \"Sci-fi\", \"Comedy\", \"Singleplayer\", \"Adventure\", \"Online Co-Op\", \"Funny\", \"Science\", \"Female Protagonist\", \"Action\", \"Story Rich\", \"Multiplayer\", \"Atmospheric\", \"Local Co-Op\", \"FPS\", \"Strategy\", \"Space\", \"Platformer\"], \n    \"title\": \"Portal 2\", \n    \"url\": \"http://store.steampowered.com/app/620/Portal_2/\"\n}\n```\n  \n\n## Model Training\n\nTo train our model on `Video` (with default hyper-parameters): \n\n```\npython main.py --dataset=Video --train_dir=default \n```\n\nor on `ml-1m`:\n\n```\npython main.py --dataset=ml-1m --train_dir=default --maxlen=200 --dropout_rate=0.2 \n``` \n\n## Misc\n\nThe implemention of self attention is modified based on *[this](https://github.com/Kyubyong/transformer)*\n\nThe convergence curve on `ml-1m`, compared with CNN/RNN based approaches:  \n\n\u003cimg src=\"curve.png\" width=\"400\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkang205%2FSASRec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkang205%2FSASRec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkang205%2FSASRec/lists"}