{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:53:42Z","timestamp":1784904822788,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3498035","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T18:37:23Z","timestamp":1731609443000},"page":"1484-1500","source":"Crossref","is-referenced-by-count":23,"title":["PATNAS: A Path-Based Training-Free Neural Architecture Search"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3622-3201","authenticated-orcid":false,"given":"Jiechao","family":"Yang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6739-621X","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Institute of China United Network Communications Corporation Limited, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Wu","sequence":"additional","affiliation":[{"name":"Research Institute of China United Network Communications Corporation Limited, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9689-0017","authenticated-orcid":false,"given":"Xibo","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"ref3","article-title":"PC-DARTS: Partial channel connections for memory-efficient architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"ref6","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00661"},{"key":"ref9","first-page":"1","article-title":"Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zela"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054824"},{"key":"ref11","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref12","first-page":"550","article-title":"Understanding and simplifying one-shot architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bender"},{"key":"ref13","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref14","first-page":"28454","article-title":"How powerful are performance predictors in neural architecture search?","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"White"},{"key":"ref15","first-page":"2020","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Kandasamy"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17233"},{"key":"ref17","first-page":"8084","article-title":"Optimal transport kernels for sequential and parallel neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref18","first-page":"12380","article-title":"NAS-bench-360: Benchmarking neural architecture search on diverse tasks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Tu"},{"key":"ref19","first-page":"28037","article-title":"NAS-bench-suite-zero: Accelerating research on zero cost proxies","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Krishnakumar"},{"key":"ref20","first-page":"33001","article-title":"Unifying and boosting gradient-based training-free neural architecture search","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref21","article-title":"GradSign: Model performance inference with theoretical insights","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"ref23","article-title":"Zero-cost proxies for lightweight NAS","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Abdelfattah"},{"key":"ref24","first-page":"7588","article-title":"Neural architecture search without training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mellor"},{"key":"ref25","first-page":"12265","article-title":"Evaluating efficient performance estimators of neural architectures","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ning"},{"key":"ref26","article-title":"Neural architecture search on Imagenet in four GPU hours: A theoretically inspired perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref27","first-page":"8580","article-title":"NASI: Label- and data-agnostic neural architecture search at initialization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shu"},{"key":"ref28","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref29","first-page":"8570","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01156"},{"key":"ref31","first-page":"17018","article-title":"Fast finite width neural tangent kernel","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Novak"},{"key":"ref32","article-title":"A deeper look at zero-cost proxies for lightweight NAS","volume-title":"Proc. Int. Conf. Learn. Representations Blog Track","author":"White"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref34","article-title":"Neural architecture search: Insights from 1000 papers","author":"White","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref36","article-title":"A tutorial on Bayesian optimization","author":"Frazier","year":"2018"},{"key":"ref37","article-title":"Interpretable neural architecture search via Bayesian optimisation with Weisfeiler-Lehman kernels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ru"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217648"},{"key":"ref39","article-title":"Learning versatile neural architectures by propagating network codes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ding"},{"key":"ref40","article-title":"Multi-conditioned graph diffusion for neural architecture search","author":"Asthana","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26169"},{"key":"ref42","first-page":"11613","article-title":"KNAS: Green neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00563"},{"key":"ref44","article-title":"Zero-shot neural architecture search: Challenges, solutions, and opportunities","author":"Li","year":"2023"},{"key":"ref45","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref46","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref47","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Tanaka"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86383-8_44"},{"key":"ref49","first-page":"61020","article-title":"MeCo: Zero-shot NAS with one data and single forward pass via minimum eigenvalue of correlation","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref50","article-title":"G-SGD: Optimizing ReLU neural networks in its positively scale-invariant space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref51","article-title":"A unified paths perspective for pruning at initialization","author":"Gebhart","year":"2021"},{"key":"ref52","first-page":"8432","article-title":"PHEW: Constructing sparse networks that learn fast and generalize well without training data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Patil"},{"key":"ref53","first-page":"15156","article-title":"Finite versus infinite neural networks: An empirical study","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref54","article-title":"Tensor programs II: Neural tangent kernel for any architecture","author":"Yang","year":"2020"},{"key":"ref55","first-page":"10835","article-title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref56","volume-title":"Gaussian Processes for Mach. Learn.","volume":"2","author":"Williams","year":"2006"},{"key":"ref57","first-page":"4134","article-title":"Bayesian optimization with robust Bayesian neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Springenberg"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"ref59","first-page":"21524","article-title":"BOTORCH: A framework for efficient Monte-Carlo Bayesian optimization","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Balandat"},{"key":"ref60","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00521"},{"key":"ref62","first-page":"7105","article-title":"NAS-bench-101: Towards reproducible neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ying"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref65","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref66","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref67","first-page":"1808","article-title":"Bridging the gap between sample-based and one-shot neural architecture search with BONAS","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref68","article-title":"NAS-bench-201: Extending the scope of reproducible neural architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dong"},{"key":"ref69","article-title":"ZiCo: Zero-shot NAS via inverse coefficient of variation on gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref70","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","volume-title":"Proc. 36th Conf. Uncertain. Artif. Intell.","author":"Li"},{"key":"ref71","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01062"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10753099.pdf?arnumber=10753099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:04:09Z","timestamp":1738821849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10753099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":73,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3498035","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}