DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search

• URL: http://arxiv.org/abs/2003.12563v1
• Date: Fri, 27 Mar 2020 17:55:21 GMT
• Title: DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search
• Authors: Xiyang Dai and Dongdong Chen and Mengchen Liu and Yinpeng Chen and Lu Yuan
• Abstract summary: Efficient search is a core issue in Neural Architecture Search (NAS) We present DA-NAS that can directly search the architecture for large-scale target tasks while allowing a large candidate set in a more efficient manner. It is 2x faster than previous methods while the accuracy is currently state-of-the-art, at 76.2% under small FLOPs constraint.
• Score: 76.9225014200746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Efficient search is a core issue in Neural Architecture Search (NAS). It is difficult for conventional NAS algorithms to directly search the architectures on large-scale tasks like ImageNet. In general, the cost of GPU hours for NAS grows with regard to training dataset size and candidate set size. One common way is searching on a smaller proxy dataset (e.g., CIFAR-10) and then transferring to the target task (e.g., ImageNet). These architectures optimized on proxy data are not guaranteed to be optimal on the target task. Another common way is learning with a smaller candidate set, which may require expert knowledge and indeed betrays the essence of NAS. In this paper, we present DA-NAS that can directly search the architecture for large-scale target tasks while allowing a large candidate set in a more efficient manner. Our method is based on an interesting observation that the learning speed for blocks in deep neural networks is related to the difficulty of recognizing distinct categories. We carefully design a progressive data adapted pruning strategy for efficient architecture search. It will quickly trim low performed blocks on a subset of target dataset (e.g., easy classes), and then gradually find the best blocks on the whole target dataset. At this time, the original candidate set becomes as compact as possible, providing a faster search in the target task. Experiments on ImageNet verify the effectiveness of our approach. It is 2x faster than previous methods while the accuracy is currently state-of-the-art, at 76.2% under small FLOPs constraint. It supports an argument search space (i.e., more candidate blocks) to efficiently search the best-performing architecture.

Related papers

• Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search [96.31315520244605]
  Arch-Graph is a transferable NAS method that predicts task-specific optimal architectures. We show Arch-Graph's transferability and high sample efficiency across numerous tasks. It is able to find top 0.16% and 0.29% architectures on average on two search spaces under the budget of only 50 models.
  arXiv  Detail & Related papers  (2022-04-12T16:46:06Z)
• When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search [117.89827740405694]
  Key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures. TNAS finds the global optimal architecture on CIFAR-10 with test accuracy of 94.37% in four GPU hours in NAS-Bench-201.
  arXiv  Detail & Related papers  (2022-04-11T07:34:21Z)
• NAS-FCOS: Efficient Search for Object Detection Architectures [113.47766862146389]
  We propose an efficient method to obtain better object detectors by searching for the feature pyramid network (FPN) and the prediction head of a simple anchor-free object detector. With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs.
  arXiv  Detail & Related papers  (2021-10-24T12:20:04Z)
• RankNAS: Efficient Neural Architecture Search by Pairwise Ranking [30.890612901949307]
  We propose a performance ranking method (RankNAS) via pairwise ranking. It enables efficient architecture search using much fewer training examples. It can design high-performance architectures while being orders of magnitude faster than state-of-the-art NAS systems.
  arXiv  Detail & Related papers  (2021-09-15T15:43:08Z)
• Core-set Sampling for Efficient Neural Architecture Search [12.272975892517039]
  This paper attempts to formulate the problem based on the data curation manner. Our key strategy is to search the architecture using summarized data distribution, i.e., core-set. In our experiments, we were able to save overall computational time from 30.8 hours to 3.5 hours, 8.8x reduction.
  arXiv  Detail & Related papers  (2021-07-08T06:19:18Z)
• Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets [42.993720854755736]
  We propose an efficient Neural Search (NAS) framework that is trained once on a database consisting of datasets and pretrained networks. We show that our model meta-learned on subsets of ImageNet-1K and architectures from NAS-Bench 201 search space successfully generalizes to multiple unseen datasets.
  arXiv  Detail & Related papers  (2021-07-02T06:33:59Z)
• Accelerating Neural Architecture Search via Proxy Data [17.86463546971522]
  We propose a novel proxy data selection method tailored for neural architecture search (NAS) executing DARTS with the proposed selection requires only 40 minutes on CIFAR-10 and 7.5 hours on ImageNet with a single GPU. When the architecture searched on ImageNet using the proposed selection is inversely transferred to CIFAR-10, a state-of-the-art test error of 2.4% is yielded.
  arXiv  Detail & Related papers  (2021-06-09T03:08:53Z)
• OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection [82.04372532783931]
  Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) We propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy.
  arXiv  Detail & Related papers  (2021-03-08T01:48:53Z)
• ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding [86.40042104698792]
  We formulate neural architecture search as a sparse coding problem. In experiments, our two-stage method on CIFAR-10 requires only 0.05 GPU-day for search. Our one-stage method produces state-of-the-art performances on both CIFAR-10 and ImageNet at the cost of only evaluation time.
  arXiv  Detail & Related papers  (2020-10-13T04:34:24Z)

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.