{"id":15035808,"url":"https://github.com/deepgraphlearning/recommendersystems","last_synced_at":"2025-04-12T17:45:48.550Z","repository":{"id":41458077,"uuid":"167231432","full_name":"DeepGraphLearning/RecommenderSystems","owner":"DeepGraphLearning","description":null,"archived":false,"fork":false,"pushed_at":"2020-04-10T09:22:29.000Z","size":51205,"stargazers_count":1112,"open_issues_count":8,"forks_count":278,"subscribers_count":32,"default_branch":"master","last_synced_at":"2025-04-03T20:11:18.011Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DeepGraphLearning.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":"2019-01-23T18:17:55.000Z","updated_at":"2025-03-22T17:13:54.000Z","dependencies_parsed_at":"2022-08-10T02:27:15.200Z","dependency_job_id":null,"html_url":"https://github.com/DeepGraphLearning/RecommenderSystems","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/DeepGraphLearning%2FRecommenderSystems","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepGraphLearning%2FRecommenderSystems/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepGraphLearning%2FRecommenderSystems/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepGraphLearning%2FRecommenderSystems/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepGraphLearning","download_url":"https://codeload.github.com/DeepGraphLearning/RecommenderSystems/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248609573,"owners_count":21132916,"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":[],"created_at":"2024-09-24T20:29:31.720Z","updated_at":"2025-04-12T17:45:48.527Z","avatar_url":"https://github.com/DeepGraphLearning.png","language":"Python","readme":"# A library of Recommender Systems\nThis repository provides a summary of our research on Recommender Systems.\nIt includes our code base on different recommendation topics, a comprehensive \nreading list and a set of bechmark data sets.\n\n## Code Base\nCurrently, we are interested in sequential recommendation, feature-based \nrecommendation and social recommendation.\n\n### *Sequential Recommedation*\nSince users' interests are naturally dynamic, modeling users' sequential behaviors \ncan learn contextual representations of users' current interests and therefore provide \nmore accurate recommendations. In this project, we include some state-of-the-art \nsequential recommenders that empoly advanced sequence modeling techniques, such as \nMarkov Chains (MCs), Recurrent Neural Networks (RNNs), Temporal Convolutional Neural\nNetworks (TCN) and Self-attentive Neural Networks (Transformer). \n\n### *Feature-based Recommendation*\nA general method for recommendation is to predict the click probabilities given \nusers' profiles and items' features, which is known as CTR prediction.\nFor CTR prediction, a core task is\nto learn (high-order) feature interactions because feature combinations are usually\npowerful indicators for prediction. However, enumerating all the possible high-order \nfeatures will exponentially increase the dimension of data, leading to a more serious \nproblem of model overfitting. In this work, we propose to learn low-dimentional \nrepresentations of combinatorial features with self-attention mechanism, by which \nfeature interactions are automatically implemented. Quantitative results show that \nour model have good prediction performance as well as satisfactory efficiency.\n\n### *Social recommendation*\nOnline social communities are an essential part of today's online experience. What we do\nor what we choose may be explicitly or implicitly influenced by our friends.\nIn this project, we study the social influences in session-based recommendations, which \nsimultaneously model users' dynamic interests and context-dependent social influences.\nFirst, we model users' dynamic interests with recurrent neural networks. \nIn order to model context-dependent social influences, we propose to employ attention-based\ngraph convolutional neural networks to differentiate friends' dynamic infuences in different \nbehavior sessions.\n\n## Reading List\nWe maintain a reading list of RecSys papers to keep track of up-to-date research.\n\n## Data List\nWe provide a summary of existing benchmark data sets for evaluating recommendation methods.\n\n## \u003cspan style=\"color:blue\"\u003eNew Data\u003c/span\u003e\nWe contribute a new large-scale dataset, which is collected from a popular movie/music/book review website Douban (www.douban.com).\nThe data set could be useful for researches on sequential recommendation, social recommendation and multi-domain recommendation.\nSee details [here](https://github.com/DeepGraphLearning/RecommenderSystems/blob/master/socialRec/README.md#douban-data).\n\n\n## Publications:\n* Weiping Song, Zhijian Duan, Ziqing Yang, Hao Zhu, Ming Zhang and Jian Tang. [Explainable Knowledge Graph-based Recommendation via Deep Reinforcement Learning](https://arxiv.org/pdf/1906.09506.pdf). arXiv'2019.\n* Weiping Song, Zhiping Xiao, Yifan Wang, Laurent Charlin, Ming Zhang and Jian Tang. \n[Session-based Social Recommendation via Dynamic Graph Attention Networks](https://arxiv.org/pdf/1902.09362.pdf). WSDM'19.\n* Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang and Jian Tang.\n[AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://arxiv.org/pdf/1810.11921.pdf).\nCIKM'2019.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepgraphlearning%2Frecommendersystems","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepgraphlearning%2Frecommendersystems","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepgraphlearning%2Frecommendersystems/lists"}