{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:31:21Z","timestamp":1726763481145},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"Predicting neural architecture performance is a challenging task and is crucial to neural architecture design and search. Existing approaches either rely on neural performance predictors which are limited to modeling architectures in a predefined design space involving specific sets of operators and connection rules, and cannot generalize to unseen architectures, or resort to Zero-Cost Proxies which are not always accurate. In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and a fuzzy clustering-based predictor ensemble. Specifically, GENNAPE represents a given neural network as a Computation Graph (CG) of atomic operations which can model an arbitrary architecture. It first learns a graph encoder via Contrastive Learning to encourage network separation by topological features, and then trains multiple predictor heads, which are soft-aggregated according to the fuzzy membership of a neural network. Experiments show that GENNAPE pretrained on NAS-Bench-101 can achieve superior transferability to 5 different public neural network benchmarks, including NAS-Bench-201, NAS-Bench-301, MobileNet and ResNet families under no or minimum fine-tuning. We further introduce 3 challenging newly labelled neural network benchmarks: HiAML, Inception and Two-Path, which can concentrate in narrow accuracy ranges. Extensive experiments show that GENNAPE can correctly discern high-performance architectures in these families. Finally, when paired with a search algorithm, GENNAPE can find architectures that improve accuracy while reducing FLOPs on three families.<\/jats:p>","DOI":"10.1609\/aaai.v37i8.26102","type":"journal-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T17:36:04Z","timestamp":1687887364000},"page":"9190-9199","source":"Crossref","is-referenced-by-count":2,"title":["GENNAPE: Towards Generalized Neural Architecture Performance Estimators"],"prefix":"10.1609","volume":"37","author":[{"given":"Keith G.","family":"Mills","sequence":"first","affiliation":[]},{"given":"Fred X.","family":"Han","sequence":"additional","affiliation":[]},{"given":"Jialin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Fabian","family":"Chudak","sequence":"additional","affiliation":[]},{"given":"Ali","family":"Safari Mamaghani","sequence":"additional","affiliation":[]},{"given":"Mohammad","family":"Salameh","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Shangling","family":"Jui","sequence":"additional","affiliation":[]},{"given":"Di","family":"Niu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2023,6,26]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/26102\/25874","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/26102\/25874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T17:36:04Z","timestamp":1687887364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/26102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,26]]},"references-count":0,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,6,27]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v37i8.26102","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6,26]]}}}