AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search

• URL: http://arxiv.org/abs/2403.19232v1
• Date: Thu, 28 Mar 2024 08:44:36 GMT
• Title: AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search
• Authors: Junghyup Lee, Bumsub Ham,
• Abstract summary: Training-free network architecture search (NAS) aims to discover high-performing networks with zero-cost proxies. We propose AZ-NAS, a novel approach that leverages the ensemble of various zero-cost proxies to enhance the correlation between a predicted ranking of networks and the ground truth. Results conclusively demonstrate the efficacy and efficiency of AZ-NAS, outperforming state-of-the-art methods on standard benchmarks.
• Score: 30.64117903216323
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training-free network architecture search (NAS) aims to discover high-performing networks with zero-cost proxies, capturing network characteristics related to the final performance. However, network rankings estimated by previous training-free NAS methods have shown weak correlations with the performance. To address this issue, we propose AZ-NAS, a novel approach that leverages the ensemble of various zero-cost proxies to enhance the correlation between a predicted ranking of networks and the ground truth substantially in terms of the performance. To achieve this, we introduce four novel zero-cost proxies that are complementary to each other, analyzing distinct traits of architectures in the views of expressivity, progressivity, trainability, and complexity. The proxy scores can be obtained simultaneously within a single forward and backward pass, making an overall NAS process highly efficient. In order to integrate the rankings predicted by our proxies effectively, we introduce a non-linear ranking aggregation method that highlights the networks highly-ranked consistently across all the proxies. Experimental results conclusively demonstrate the efficacy and efficiency of AZ-NAS, outperforming state-of-the-art methods on standard benchmarks, all while maintaining a reasonable runtime cost.

Related papers

• Surprisingly Strong Performance Prediction with Neural Graph Features [35.54664728425731]
  We propose neural graph features (GRAF) to compute properties of architectural graphs. GRAF offers fast and interpretable performance prediction while outperforming zero-cost proxies. In combination with other zero-cost proxies, GRAF outperforms most existing performance predictors at a fraction of the cost.
  arXiv  Detail & Related papers  (2024-04-25T12:07:41Z)
• TG-NAS: Leveraging Zero-Cost Proxies with Transformer and Graph Convolution Networks for Efficient Neural Architecture Search [1.30891455653235]
  TG-NAS aims to create training-free proxies for architecture performance prediction. We introduce TG-NAS, a novel model-based universal proxy that leverages a transformer-based operator embedding generator and a graph convolution network (GCN) to predict architecture performance. TG-NAS achieves up to 300X improvements in search efficiency compared to previous SOTA ZC proxy methods.
  arXiv  Detail & Related papers  (2024-03-30T07:25:30Z)
• Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations [59.683234126055694]
  Recent neural architecture search (NAS) frameworks have been successful in finding optimal architectures for given conditions. We propose a novel lightweight robust zero-cost proxy that considers the consistency across features, parameters, and gradients of both clean and perturbed images. Our approach facilitates an efficient and rapid search for neural architectures capable of learning generalizable features that exhibit robustness across diverse perturbations.
  arXiv  Detail & Related papers  (2023-06-08T08:34:26Z)
• $\beta$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search [96.99525100285084]
  Regularization method, Beta-Decay, is proposed to regularize the DARTS-based NAS searching process (i.e., $beta$-DARTS) In-depth theoretical analyses on how it works and why it works are provided.
  arXiv  Detail & Related papers  (2023-01-16T12:30:32Z)
• ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies [30.059154132130207]
  We present ProxyBO, an efficient Bayesian optimization framework that utilizes zero-cost proxies to accelerate neural architecture search. We show that ProxyBO consistently outperforms competitive baselines on five tasks from three public benchmarks.
  arXiv  Detail & Related papers  (2021-10-20T08:18:16Z)
• GradSign: Model Performance Inference with Theoretical Insights [2.4112990554464235]
  We propose GradSign, an accurate, simple, and flexible metric for model performance inference with theoretical insights. We show that GradSign generalizes well to real-world networks and consistently outperforms state-of-the-art gradient-based methods for MPI evaluated by Spearman's rho and Kendall's Tau.
  arXiv  Detail & Related papers  (2021-10-16T17:03:10Z)
• Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics [117.4281417428145]
  This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS) NAS has been explosively studied to automate the discovery of top-performer neural networks, but suffers from heavy resource consumption and often incurs search bias due to truncated training or approximations. We present a unified framework to understand and accelerate NAS, by disentangling "TEG" characteristics of searched networks.
  arXiv  Detail & Related papers  (2021-08-26T17:52:07Z)
• Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search [70.57382341642418]
  Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. Recent works have empirically shown a ranking disorder between the performance of stand-alone architectures and that of the corresponding shared-weight networks. We propose a regularization term that aims to maximize the correlation between the performance rankings of the shared-weight network and that of the standalone architectures.
  arXiv  Detail & Related papers  (2021-04-12T09:32:33Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)
• EcoNAS: Finding Proxies for Economical Neural Architecture Search [130.59673917196994]
  In this paper, we observe that most existing proxies exhibit different behaviors in maintaining the rank consistency among network candidates. Inspired by these observations, we present a reliable proxy and further formulate a hierarchical proxy strategy. The strategy spends more computations on candidate networks that are potentially more accurate, while discards unpromising ones in early stage with a fast proxy.
  arXiv  Detail & Related papers  (2020-01-05T13:29:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.