Generative Adversarial Neural Architecture Search with Importance Sampling
Bibliographic record
Abstract
Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess. The variation in search spaces adopted has further affected a fair comparison between search strategies. In this paper, we focus on search strategies in NAS and propose Generative Adversarial NAS (GA-NAS), promoting stable and reproducible neural architecture search. GA-NAS is theoretically inspired by importance sampling for rare event simulation, and iteratively refits a generator to previously discovered top architectures, thus increasingly focusing on important parts of the search space. We propose an efficient adversarial learning approach in GA-NAS, where the generator is not trained based on a large number of observations on architecture performance, but based on the relative prediction made by a discriminator, thus significantly reducing the number of evaluations required. Extensive experiments show that GA-NAS beats the best published results under several cases on the public NAS benchmarks including NAS-Bench-101, NAS-Bench-201, and NAS-Bench-301. We further show that GA-NAS can handle ad-hoc search constraints and search spaces. GA-NAS can find new architectures that enhance EfficientNet and ProxylessNAS in terms of ImageNet Top-1 accuracy and/or the number of parameters by searching in their original search spaces.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".