{"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/irgan-a-minimax-game-for-unifying-generative","title":"IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models","arxiv_id":"1705.10513","date":"2017-05-30","proceeding":null,"authors":["Jun Wang","Lantao Yu","Wei-Nan Zhang","Yu Gong","Yinghui Xu","Benyou Wang","Peng Zhang","Dell Zhang"],"abstract":"This paper provides a unified account of two schools of thinking in\ninformation retrieval modelling: the generative retrieval focusing on\npredicting relevant documents given a query, and the discriminative retrieval\nfocusing on predicting relevancy given a query-document pair. We propose a game\ntheoretical minimax game to iteratively optimise both models. On one hand, the\ndiscriminative model, aiming to mine signals from labelled and unlabelled data,\nprovides guidance to train the generative model towards fitting the underlying\nrelevance distribution over documents given the query. On the other hand, the\ngenerative model, acting as an attacker to the current discriminative model,\ngenerates difficult examples for the discriminative model in an adversarial way\nby minimising its discrimination objective. With the competition between these\ntwo models, we show that the unified framework takes advantage of both schools\nof thinking: (i) the generative model learns to fit the relevance distribution\nover documents via the signals from the discriminative model, and (ii) the\ndiscriminative model is able to exploit the unlabelled data selected by the\ngenerative model to achieve a better estimation for document ranking. Our\nexperimental results have demonstrated significant performance gains as much as\n23.96% on Precision@5 and 15.50% on MAP over strong baselines in a variety of\napplications including web search, item recommendation, and question answering.","url_abs":"http://arxiv.org/abs/1705.10513v2","url_pdf":"http://arxiv.org/pdf/1705.10513v2.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":"irgan-a-minimax-game-for-unifying-generative","repo_url":"https://github.com/geek-ai/irgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"irgan-a-minimax-game-for-unifying-generative","repo_url":"https://github.com/iYiYaHa/PyTorch-IRGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"irgan-a-minimax-game-for-unifying-generative","repo_url":"https://github.com/hwang1996/IRGAN-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"ad-hoc-information-retrieval","task_name":"Ad-Hoc Information Retrieval"},{"task_slug":"document-ranking","task_name":"Document Ranking"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10513"}},"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/hwang1996/IRGAN-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/geek-ai/irgan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iYiYaHa/PyTorch-IRGAN","reach":{"status":"unanswered"}}],"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":"d7922f9236df52f5","entry":"log_time_delta","repo":"geek-ai/irgan","repo_kind":"official","path":"Question-Answer/irgan.py","file_url":"https://github.com/geek-ai/irgan/blob/HEAD/Question-Answer/irgan.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7922f9236df52f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}