{"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/real-world-large-scale-recommendation-systems","title":"Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations","arxiv_id":"2202.06499","date":"2022-02-14","proceeding":null,"authors":["Gil I. Shamir","Dong Lin"],"abstract":"Real world recommendation systems influence a constantly growing set of domains. With deep networks, that now drive such systems, recommendations have been more relevant to the user's interests and tasks. However, they may not always be reproducible even if produced by the same system for the same user, recommendation sequence, request, or query. This problem received almost no attention in academic publications, but is, in fact, very realistic and critical in real production systems. We consider reproducibility of real large scale deep models, whose predictions determine such recommendations. We demonstrate that the celebrated Rectified Linear Unit (ReLU) activation, used in deep models, can be a major contributor to irreproducibility. We propose the use of smooth activations to improve recommendation reproducibility. We describe a novel family of smooth activations; Smooth ReLU (SmeLU), designed to improve reproducibility with mathematical simplicity, with potentially cheaper implementation. SmeLU is a member of a wider family of smooth activations. While other techniques that improve reproducibility in real systems usually come at accuracy costs, smooth activations not only improve reproducibility, but can even give accuracy gains. We report metrics from real systems in which we were able to productionalize SmeLU with substantial reproducibility gains and better accuracy-reproducibility trade-offs. These include click-through-rate (CTR) prediction systems, content, and application recommendation systems.","url_abs":"https://arxiv.org/abs/2202.06499v1","url_pdf":"https://arxiv.org/pdf/2202.06499v1.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":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/ChristophReich1996/SmeLU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/ChristophReich1996/SmeLU-Triton","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/1hb6s7t/SmeLU-ms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/SmeLU-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/MindSpore-scientific/code-1/tree/main/SmeLU-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/MindSpore-scientific/code-11/tree/main/SmeLU-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/MindSpore-scientific/code-13/tree/main/SmeLU-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"real-world-large-scale-recommendation-systems","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/SmeLU-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"click-through-rate-prediction","task_name":"Click-Through Rate Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"smelu","method_name":"SmeLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"ChristophReich1996/SmeLU","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ChristophReich1996/SmeLU-Triton","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"1hb6s7t/SmeLU-ms","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-scientific-2/code-10","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2412.06329"],"harvested_for_calls":[{"arxiv_id":"2412.06329","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.06329"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.06329\")"}]},{"repo":"MindSpore-scientific/code-1","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.12624"],"harvested_for_calls":[{"arxiv_id":"2210.12624","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.12624"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.12624\")"}]},{"repo":"MindSpore-scientific/code-11","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.16372"],"harvested_for_calls":[{"arxiv_id":"2403.16372","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.16372"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.16372\")"}]},{"repo":"MindSpore-scientific/code-13","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.16476"],"harvested_for_calls":[{"arxiv_id":"2312.16476","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.16476"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.16476\")"}]},{"repo":"pwc-1/Paper-9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.13719"],"harvested_for_calls":[{"arxiv_id":"1909.13719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.13719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.13719\")"}]}],"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":"347b6cf1ccf05a78d0b1a22cddca9d3b1f04ee36284d35674fd36cbc0dddc724","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}