{"id":15649072,"url":"https://github.com/shibing624/rater","last_synced_at":"2025-04-30T14:44:26.259Z","repository":{"id":57460147,"uuid":"275549860","full_name":"shibing624/rater","owner":"shibing624","description":"rater, recommender systems. 推荐模型，包括：DeepFM，Wide\u0026Deep，DIN，DeepWalk，Node2Vec等模型实现，开箱即用。","archived":false,"fork":false,"pushed_at":"2020-09-01T15:04:52.000Z","size":44095,"stargazers_count":44,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-08T20:07:53.946Z","etag":null,"topics":["algorithms","ctr-models","deepfm","ffm","pnn","rater","recommendation-system","wide-and-deep","xdeepfm"],"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/shibing624.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":"2020-06-28T09:20:37.000Z","updated_at":"2025-01-21T07:46:08.000Z","dependencies_parsed_at":"2022-08-28T13:52:48.182Z","dependency_job_id":null,"html_url":"https://github.com/shibing624/rater","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Frater","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Frater/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Frater/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Frater/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624","download_url":"https://codeload.github.com/shibing624/rater/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251723310,"owners_count":21633134,"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":["algorithms","ctr-models","deepfm","ffm","pnn","rater","recommendation-system","wide-and-deep","xdeepfm"],"created_at":"2024-10-03T12:27:36.473Z","updated_at":"2025-04-30T14:44:26.237Z","avatar_url":"https://github.com/shibing624.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# rater\n\n**rater** is a comparative framework for multimodal recommender systems. It was developed to facilitate the designing, comparing, and sharing of recommendation models.\n\n## Feature\n\n* easy to use, rebuild and compare\n* SOTA model\n* classical model and deep model\n* model has great influence in the industry\n* model hsa been successfully applied by Google, Alibaba, Baidu and other well-known companies\n* engineering oriented, not just experimental data validation\n\n\n## Data\n\n1. ml-1m: http://files.grouplens.org/datasets/movielens/ml-1m.zip\n2. delicious-2k: http://files.grouplens.org/datasets/hetrec2011/hetrec2011-delicious-2k.zip\n3. lastfm-dataset-360K: http://mtg.upf.edu/static/datasets/last.fm/lastfm-dataset-360K.tar.gz\n4. slashdot: http://snap.stanford.edu/data/soc-Slashdot0902.txt.gz\n5. epinions: http://snap.stanford.edu/data/soc-Epinions1.txt.gz\n6. ml-100k: http://files.grouplens.org/datasets/movielens/ml-100k.zip\n7. Criteo(dac full): https://s3-eu-west-1.amazonaws.com/kaggle-display-advertising-challenge-dataset/dac.tar.gz\n8. Criteo(dac sample): http://labs.criteo.com/wp-content/uploads/2015/04/dac_sample.tar.gz\n\n## Install\n```\npip3 install rater\n```\n\nor\n\n```\ngit clone https://github.com/shibing624/rater.git\ncd rater\npython3 setup.py install\n```\n\n## Usage\n\n\nLoad the built-in [MovieLens 1M](https://grouplens.org/datasets/movielens/1m/) dataset (will be downloaded if not cached):\n\n\n\n**Output:**\n\n|                          |    MAE |   RMSE |    AUC | NDCG@10 | Recall@10 | Train (s) | Test (s) |\n| ------------------------ | -----: | -----: | -----: | ------: | --------: | ---------: | -------: |\n| [MF]  | 0.7430 | 0.8998 | 0.7445 |  0.0479 |  0.0352 |    0.13 |     1.57 |\n\nFor more details, please take a look at our [examples](examples).\n\n## Models\n\nThe models supported are listed below. Why don't you join us to lengthen the list?\n\n### Click Through Rate Prediction\n| model | paper |\n|:-----|:------|\n|LR: Logistic Regression| [Simple and Scalable Response Prediction for Display Advertising](https://dl.acm.org/doi/pdf/10.1145/2532128?download=true)|\n|FM: Factorization Machine|\\[ICDM 2010\\][Factorization Machines](https://dl.acm.org/doi/10.1109/ICDM.2010.127)|\n|GBDT+LR: Gradient Boosting Tree with Logistic Regression|[Practical Lessons from Predicting Clicks on Ads at Facebook](https://dl.acm.org/doi/pdf/10.1145/2648584.2648589)|\n|FNN: Factorization-supported Neural Network|\\[ECIR 2016\\][Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction](https://dl.acm.org/doi/pdf/10.1145/2959100.2959134)|\n|PNN: Product-based Neural Network|\\[ICDM 2016\\][Product-based neural networks for user response prediction](https://arxiv.org/pdf/1611.00144.pdf)|\n|Wide and Deep|\\[DLRS 2016\\][Wide \u0026 Deep Learning for Recommender Systems](https://arxiv.org/pdf/1606.07792.pdf)|\n|DeepFM|\\[IJCAI 2017\\][DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://arxiv.org/pdf/1703.04247.pdf)|\n|AFM: Attentional Factorization Machine|\\[IJCAI 2017\\][Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](http://www.ijcai.org/proceedings/2017/435)|\n|NFM: Neural Factorization Machine|\\[SIGIR 2017\\][Neural Factorization Machines for Sparse Predictive Analytics](https://arxiv.org/pdf/1708.05027.pdf)|\n|FFM: Field-aware Factorization Machine|\\[RecSys 2016\\][Field-aware Factorization Machines for CTR Prediction](https://dl.acm.org/doi/pdf/10.1145/2959100.2959134)|\n|CCPM: Convolutional Click Prediction Model|\\[CIKM 2015\\][A Convolutional Click Prediction Model](http://ir.ia.ac.cn/bitstream/173211/12337/1/A%20Convolutional%20Click%20Prediction%20Model.pdf)|\n|Piece-wise Linear Model|\\[arxiv 2017\\][Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction](https://arxiv.org/abs/1704.05194)|\n|DCN: Deep \u0026 Cross Network|\\[ADKDD 2017\\][Deep \u0026 Cross Network for Ad Click Predictions](https://arxiv.org/abs/1708.05123)|\n|xDeepFM|\\[KDD 2018\\][xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://arxiv.org/pdf/1803.05170.pdf)|\n|AutoInt|\\[arxiv 2018\\][AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://arxiv.org/abs/1810.11921)|\n|ONN|\\[arxiv 2019\\][Operation-aware Neural Networks for User Response Prediction](https://arxiv.org/pdf/1904.12579.pdf)|\n|FGCNN|\\[WWW 2019\\][Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1904.04447)|\n|FiBiNET|\\[RecSys 2019\\][FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction](https://arxiv.org/pdf/1905.09433.pdf)|\n|FLEN|\\[arxiv 2019\\][FLEN: Leveraging Field for Scalable CTR Prediction](https://arxiv.org/pdf/1911.04690.pdf)|\n\n\n### Sequential Recommendation\n| model/keywords | paper |\n|:------|:------|\n|GRU4Rec|Session-based Recommendations with Recurrent Neural Networks|\n|Caser|Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding|\n|DIN: Deep Interest Network|\\[KDD 2018\\][Deep Interest Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1706.06978.pdf)|\n|Self-Attention |Next Item Recommendation with Self-Attention|\n|Hierarchical Attention |Sequential Recommender System based on Hierarchical Attention Networks|\n|DIEN: Deep Interest Evolution Network|\\[AAAI 2019\\][Deep Interest Evolution Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1809.03672.pdf)|\n|DISN: Deep Session Interest Network|\\[IJCAI 2019\\][Deep Session Interest Network for Click-Through Rate Prediction](https://arxiv.org/abs/1905.06482)|\n\n\n### Embedding Methods\n| model | paper |\n|:------|:------|\n|node2vec|node2vec: Scalable Feature Learning for Networks|\n|item2vec|ITEM2VEC: Neural item embedding for collaborative filtering|\n|Airbnb embedding|Real-time Personalization using Embeddings for Search Ranking at Airbnb|\n|EGES: Enhanced Graph Embedding with Side information|Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba|\n\n\n#### Model Evolution\n\n![model_evolution](docs/deeprec.jpg)\nrefer: https://zhuanlan.zhihu.com/p/63186101\n\n\n## Contribute\n\n\nYour contributions at any level of the library are welcome. If you intend to contribute, please:\n  - Fork the rater repository to your own account.\n  - Make changes and create pull requests.\n\nYou can also post bug reports and feature requests in [GitHub issues](https://github.com/shibing624/rater/issues).\n\n## License\n\n[Apache License 2.0](LICENSE)\n\n\n\n## Reference\n\n\n* [Multilayer Perceptron Based Recommendation]\n* [Autoencoder Based Recommendation]\n* [CNN Based Recommendation]\n* [RNN Based Recommendation]\n* [Restricted Boltzmann Machine Based Recommendation]\n* [Neural Attention Based Recommendation]\n* [Neural AutoRegressive Based Recommendation]\n* [Deep Reinforcement Learning for Recommendation]\n* [GAN Based Recommendation]\n* [Deep Hybrid Models for Recommendation]\n* [maciejkula/spotlight](https://github.com/maciejkula/spotlight)\n* [shenweichen/DeepCTR](https://github.com/shenweichen/DeepCTR)\n* [Magic-Bubble/RecommendSystemPractice](https://github.com/Magic-Bubble/RecommendSystemPractice)\n* [nzc/dnn_ctr](https://github.com/nzc/dnn_ctr)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshibing624%2Frater","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshibing624%2Frater","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshibing624%2Frater/lists"}