{"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/jointly-learning-explainable-rules-for","title":"Jointly Learning Explainable Rules for Recommendation with Knowledge Graph","arxiv_id":"1903.03714","date":"2019-03-09","proceeding":null,"authors":["Weizhi Ma","Min Zhang","Yue Cao","Woojeong","Jin","Chenyang Wang","Yiqun Liu","Shaoping Ma","Xiang Ren"],"abstract":"Explainability and effectiveness are two key aspects for building recommender\nsystems. Prior efforts mostly focus on incorporating side information to\nachieve better recommendation performance. However, these methods have some\nweaknesses: (1) prediction of neural network-based embedding methods are hard\nto explain and debug; (2) symbolic, graph-based approaches (e.g., meta\npath-based models) require manual efforts and domain knowledge to define\npatterns and rules, and ignore the item association types (e.g. substitutable\nand complementary). In this paper, we propose a novel joint learning framework\nto integrate \\textit{induction of explainable rules from knowledge graph} with\n\\textit{construction of a rule-guided neural recommendation model}. The\nframework encourages two modules to complement each other in generating\neffective and explainable recommendation: 1) inductive rules, mined from\nitem-centric knowledge graphs, summarize common multi-hop relational patterns\nfor inferring different item associations and provide human-readable\nexplanation for model prediction; 2) recommendation module can be augmented by\ninduced rules and thus have better generalization ability dealing with the\ncold-start issue. Extensive experiments\\footnote{Code and data can be found at:\n\\url{https://github.com/THUIR/RuleRec}} show that our proposed method has\nachieved significant improvements in item recommendation over baselines on\nreal-world datasets. Our model demonstrates robust performance over \"noisy\"\nitem knowledge graphs, generated by linking item names to related entities.","url_abs":"http://arxiv.org/abs/1903.03714v1","url_pdf":"http://arxiv.org/pdf/1903.03714v1.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":"jointly-learning-explainable-rules-for","repo_url":"https://github.com/THUIR/RuleRec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"explainable-recommendation","task_name":"Explainable Recommendation"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03714"}},"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/THUIR/RuleRec","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"7b39eb74b0bdf784","entry":"getItemEnDic","repo":"THUIR/RuleRec","repo_kind":"official","path":"RuleLearning/getFeatures.py","file_url":"https://github.com/THUIR/RuleRec/blob/HEAD/RuleLearning/getFeatures.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7b39eb74b0bdf784"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}