{"ID":2825715,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20112","arxiv_id":"2512.20112","title":"Evolutionary Neural Architecture Search with Dual Contrastive Learning","abstract":"Evolutionary Neural Architecture Search (ENAS) has gained attention for automatically designing neural network architectures. Recent studies use a neural predictor to guide the process, but the high computational costs of gathering training data -- since each label requires fully training an architecture -- make achieving a high-precision predictor with { limited compute budget (i.e., a capped number of fully trained architecture-label pairs)} crucial for ENAS success. This paper introduces ENAS with Dual Contrastive Learning (DCL-ENAS), a novel method that employs two stages of contrastive learning to train the neural predictor. In the first stage, contrastive self-supervised learning is used to learn meaningful representations from neural architectures without requiring labels. In the second stage, fine-tuning with contrastive learning is performed to accurately predict the relative performance of different architectures rather than their absolute performance, which is sufficient to guide the evolutionary search. Across NASBench-101 and NASBench-201, DCL-ENAS achieves the highest validation accuracy, surpassing the strongest published baselines by 0.05\\% (ImageNet16-120) to 0.39\\% (NASBench-101). On a real-world ECG arrhythmia classification task, DCL-ENAS improves performance by approximately 2.5 percentage points over a manually designed, non-NAS model obtained via random search, while requiring only 7.7 GPU-days.","short_abstract":"Evolutionary Neural Architecture Search (ENAS) has gained attention for automatically designing neural network architectures. Recent studies use a neural predictor to guide the process, but the high computational costs of gathering training data -- since each label requires fully training an architecture -- make achiev...","url_abs":"https://arxiv.org/abs/2512.20112","url_pdf":"https://arxiv.org/pdf/2512.20112v1","authors":"[\"Xian-Rong Zhang\",\"Yue-Jiao Gong\",\"Wei-Neng Chen\",\"Jun Zhang\"]","published":"2025-12-23T07:15:38Z","proceeding":"cs.NE","tasks":"[\"cs.NE\",\"cs.AI\"]","methods":"[]","has_code":false}