{"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/transnas-bench-101-improving-transferrability","title":"TransNAS-Bench-101: Improving Transferrability and Generalizability of Cross-Task Neural Architecture Search","arxiv_id":null,"date":"2021-01-01","proceeding":null,"authors":["Yawen Duan","Xin Chen","Hang Xu","Zewei Chen","Xiaodan Liang","Tong Zhang","Zhenguo Li"],"abstract":"Recent breakthroughs of Neural Architecture Search (NAS) are extending the field's research scope towards a broader range of vision tasks and more diversified search spaces. While existing NAS methods mostly design architectures on one single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks. Many of them leverage transfer learning and seek to preserve, reuse, and refine network design knowledge to achieve higher efficiency in future tasks. However, the huge computational cost and experiment complexity of cross-task NAS are imposing barriers for valuable research in this direction. Existing transferrable NAS algorithms are also based on different settings, e.g., datasets and search spaces, which raises concerns on performance comparability. Although existing NAS benchmarks provided some solutions, they all focus on one single type of vision task, i.e., classification. In this work, we propose TransNAS-Bench-101, a benchmark containing network performance across 7 tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks. This diversity provides opportunities to transfer NAS methods among the tasks, and allows for more complex transfer schemes to evolve. We explore two fundamentally different types of search spaces: cell-level search space and macro-level search space. With 7,352 backbones evaluated on 7 tasks, 51,464 trained models with detailed training information are provided. Generating this benchmark takes about 193,760 GPU hours, which is equivalent to 22.12 years of computation on a single Nvidia V100 GPU. Analysis of 4 benchmark transfer schemes highlights that: (1) Direct deployment of both architectures and policies can easily lead to negative transfer unless guided by carefully designed mechanisms. (2) Evolutionary methods' role in transferrable NAS might be overlooked in the past. (3) It is a valid challenge for NAS algorithms to perform well across tasks and search spaces consistently. We also provide our suggestions for future research along with the analysis. With TransNAS-Bench-101, we hope to encourage the advent of exceptional NAS algorithms that raise cross-task search efficiency and generalizability to the next level.","url_abs":"https://openreview.net/forum?id=HUd2wQ0j200","url_pdf":"https://openreview.net/pdf?id=HUd2wQ0j200","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":"transnas-bench-101-improving-transferrability","repo_url":"https://github.com/kmdanielduan/TransNASBench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transnas-bench-101-improving-transferrability","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/DDM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"kmdanielduan/TransNASBench","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2105.11871"],"harvested_for_calls":[{"arxiv_id":"2105.11871","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.11871"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.11871\")"}]},{"repo":"mindspore-ai/models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.08084"],"harvested_for_calls":[{"arxiv_id":"2208.08084","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.08084"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.08084\")"}]}],"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":"f516d5cd7469b7f93bc0b63935fd96ad528b644eceb141e6a2ea55d95b713042","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}