{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-interest-network-with-dynamic-routing","title":"Multi-Interest Network with Dynamic Routing for Recommendation at Tmall","arxiv_id":"1904.08030","date":"2019-04-17","proceeding":null,"authors":["Chao Li","Zhiyuan Liu","Mengmeng Wu","Yuchi Xu","Pipei Huang","Huan Zhao","Guoliang Kang","Qiwei Chen","Wei Li","Dik Lun Lee"],"abstract":"Industrial recommender systems usually consist of the matching stage and the\nranking stage, in order to handle the billion-scale of users and items. The\nmatching stage retrieves candidate items relevant to user interests, while the\nranking stage sorts candidate items by user interests. Thus, the most critical\nability is to model and represent user interests for either stage. Most of the\nexisting deep learning-based models represent one user as a single vector which\nis insufficient to capture the varying nature of user's interests. In this\npaper, we approach this problem from a different view, to represent one user\nwith multiple vectors encoding the different aspects of the user's interests.\nWe propose the Multi-Interest Network with Dynamic routing (MIND) for dealing\nwith user's diverse interests in the matching stage. Specifically, we design a\nmulti-interest extractor layer based on capsule routing mechanism, which is\napplicable for clustering historical behaviors and extracting diverse\ninterests. Furthermore, we develop a technique named label-aware attention to\nhelp learn a user representation with multiple vectors. Through extensive\nexperiments on several public benchmarks and one large-scale industrial dataset\nfrom Tmall, we demonstrate that MIND can achieve superior performance than\nstate-of-the-art methods for recommendation. Currently, MIND has been deployed\nfor handling major online traffic at the homepage on Mobile Tmall App.","url_abs":"http://arxiv.org/abs/1904.08030v1","url_pdf":"http://arxiv.org/pdf/1904.08030v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-interest-network-with-dynamic-routing","repo_url":"https://github.com/UlionTse/mlgb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-interest-network-with-dynamic-routing","repo_url":"https://github.com/Wang-Yu-Qing/MIND","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-interest-network-with-dynamic-routing","repo_url":"https://github.com/shenweichen/deepmatch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-interest-network-with-dynamic-routing","repo_url":"https://github.com/PaddlePaddle/PaddleRec/tree/release/2.1.0/models/recall/mind","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"multi-interest-network-with-dynamic-routing","repo_url":"https://github.com/alibaba/TorchEasyRec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"multi-interest-network-with-dynamic-routing","repo_url":"https://github.com/alibaba/easyrec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/information-retrieval-on-amazon","task":"Information Retrieval","dataset":"Amazon","model":"MIND","rank_in_archive_order":1,"of":1,"metrics":{"HR@30":"0.32"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.08030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08030"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shenweichen/deepmatch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleRec/tree/release/2.1.0/models/recall/mind","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/easyrec","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/TorchEasyRec","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Wang-Yu-Qing/MIND","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UlionTse/mlgb","reach":{"status":"unanswered"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f4f7e333e0b42f6b","entry":"genUserTestSamples","repo":"Wang-Yu-Qing/MIND","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Wang-Yu-Qing/MIND/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4f7e333e0b42f6b"}},{"code_sha256_prefix":"d4989c0c48ba7e83","entry":"genUserTrainSamples","repo":"Wang-Yu-Qing/MIND","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Wang-Yu-Qing/MIND/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4989c0c48ba7e83"}},{"code_sha256_prefix":"292a6deb827c878d","entry":"padOrCut","repo":"Wang-Yu-Qing/MIND","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Wang-Yu-Qing/MIND/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"292a6deb827c878d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}