{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/twin-two-stage-interest-network-for-lifelong","title":"TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou","arxiv_id":"2302.02352","date":"2023-02-05","proceeding":null,"authors":["Jianxin Chang","Chenbin Zhang","Zhiyi Fu","Xiaoxue Zang","Lin Guan","Jing Lu","Yiqun Hui","Dewei Leng","Yanan Niu","Yang song","Kun Gai"],"abstract":"Life-long user behavior modeling, i.e., extracting a user's hidden interests from rich historical behaviors in months or even years, plays a central role in modern CTR prediction systems. Conventional algorithms mostly follow two cascading stages: a simple General Search Unit (GSU) for fast and coarse search over tens of thousands of long-term behaviors and an Exact Search Unit (ESU) for effective Target Attention (TA) over the small number of finalists from GSU. Although efficient, existing algorithms mostly suffer from a crucial limitation: the \\textit{inconsistent} target-behavior relevance metrics between GSU and ESU. As a result, their GSU usually misses highly relevant behaviors but retrieves ones considered irrelevant by ESU. In such case, the TA in ESU, no matter how attention is allocated, mostly deviates from the real user interests and thus degrades the overall CTR prediction accuracy. To address such inconsistency, we propose \\textbf{TWo-stage Interest Network (TWIN)}, where our Consistency-Preserved GSU (CP-GSU) adopts the identical target-behavior relevance metric as the TA in ESU, making the two stages twins. Specifically, to break TA's computational bottleneck and extend it from ESU to GSU, or namely from behavior length $10^2$ to length $10^4-10^5$, we build a novel attention mechanism by behavior feature splitting. For the video inherent features of a behavior, we calculate their linear projection by efficient pre-computing \\& caching strategies. And for the user-item cross features, we compress each into a one-dimentional bias term in the attention score calculation to save the computational cost. The consistency between two stages, together with the effective TA-based relevance metric in CP-GSU, contributes to significant performance gain in CTR prediction.","url_abs":"https://arxiv.org/abs/2302.02352v2","url_pdf":"https://arxiv.org/pdf/2302.02352v2.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":"twin-two-stage-interest-network-for-lifelong","repo_url":"https://github.com/paper-submission-coder/seminar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"twin-two-stage-interest-network-for-lifelong","repo_url":"https://github.com/reczoo/FuxiCTR/tree/main/model_zoo/LongCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"click-through-rate-prediction","task_name":"Click-Through Rate Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.02352","atlas_url":"https://app.syntology.ai/?focus=2302.02352","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2302.02352"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2302.02352\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2302.02352"},"call":"get_concepts_for_paper(arxiv_id=\"2302.02352\")"}],"by_repo":[{"repo":"paper-submission-coder/seminar","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"reczoo/FuxiCTR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2304.00902"],"harvested_for_calls":[{"arxiv_id":"2304.00902","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.00902"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.00902\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2104bb8596380d37db3099c165c1856cabaaed6943a3044921ac61caa3d3b1cc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}