{"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-task-feature-learning-for-knowledge","title":"Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation","arxiv_id":"1901.08907","date":"2019-01-23","proceeding":null,"authors":["Hongwei Wang","Fuzheng Zhang","Miao Zhao","Wenjie Li","Xing Xie","Minyi Guo"],"abstract":"Collaborative filtering often suffers from sparsity and cold start problems\nin real recommendation scenarios, therefore, researchers and engineers usually\nuse side information to address the issues and improve the performance of\nrecommender systems. In this paper, we consider knowledge graphs as the source\nof side information. We propose MKR, a Multi-task feature learning approach for\nKnowledge graph enhanced Recommendation. MKR is a deep end-to-end framework\nthat utilizes knowledge graph embedding task to assist recommendation task. The\ntwo tasks are associated by cross&compress units, which automatically share\nlatent features and learn high-order interactions between items in recommender\nsystems and entities in the knowledge graph. We prove that cross&compress units\nhave sufficient capability of polynomial approximation, and show that MKR is a\ngeneralized framework over several representative methods of recommender\nsystems and multi-task learning. Through extensive experiments on real-world\ndatasets, we demonstrate that MKR achieves substantial gains in movie, book,\nmusic, and news recommendation, over state-of-the-art baselines. MKR is also\nshown to be able to maintain a decent performance even if user-item\ninteractions are sparse.","url_abs":"http://arxiv.org/abs/1901.08907v1","url_pdf":"http://arxiv.org/pdf/1901.08907v1.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-task-feature-learning-for-knowledge","repo_url":"https://github.com/hwwang55/MKR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-task-feature-learning-for-knowledge","repo_url":"https://github.com/hsientzucheng/MKR.PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-task-feature-learning-for-knowledge","repo_url":"https://github.com/hwwang55/KGCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"news-recommendation","task_name":"News Recommendation"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/click-through-rate-prediction-on-childrens","task":"Click-Through Rate Prediction","dataset":"Children's Book Test Common noun","model":"MKR","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"0.734","Accuracy":"70.4"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-lastfm","task":"Click-Through Rate Prediction","dataset":"Last.FM","model":"MKR","rank_in_archive_order":2,"of":2,"metrics":{"AUC":"0.689","Accuracy":"64.5"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-movielens-1m","task":"Click-Through Rate Prediction","dataset":"MovieLens 1M","model":"MKR","rank_in_archive_order":4,"of":6,"metrics":{"AUC":"0.917","Accuracy":"84.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.08907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08907"}},"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/hsientzucheng/MKR.PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hwwang55/KGCN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hwwang55/MKR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"00773b90aacb7b2d","entry":"dataset_split","repo":"hwwang55/MKR","repo_kind":"official","path":"src/data_loader.py","file_url":"https://github.com/hwwang55/MKR/blob/HEAD/src/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00773b90aacb7b2d"}},{"code_sha256_prefix":"df1bf46ed02ef952","entry":"get_layer_id","repo":"hwwang55/MKR","repo_kind":"official","path":"src/layers.py","file_url":"https://github.com/hwwang55/MKR/blob/HEAD/src/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df1bf46ed02ef952"}},{"code_sha256_prefix":"a09f0a8d57e1f250","entry":"load_data","repo":"hwwang55/MKR","repo_kind":"official","path":"src/data_loader.py","file_url":"https://github.com/hwwang55/MKR/blob/HEAD/src/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a09f0a8d57e1f250"}},{"code_sha256_prefix":"5a6432bdaededcdd","entry":"load_rating","repo":"hwwang55/MKR","repo_kind":"official","path":"src/data_loader.py","file_url":"https://github.com/hwwang55/MKR/blob/HEAD/src/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a6432bdaededcdd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}