Flexible Channel Dimensions for Differentiable Architecture Search

• URL: http://arxiv.org/abs/2306.08021v1
• Date: Tue, 13 Jun 2023 15:21:38 GMT
• Title: Flexible Channel Dimensions for Differentiable Architecture Search
• Authors: Ahmet Caner Y\"uz\"ug\"uler and Nikolaos Dimitriadis and Pascal Frossard
• Abstract summary: We propose a novel differentiable neural architecture search method with an efficient dynamic channel allocation algorithm. We show that the proposed framework is able to find DNN architectures that are equivalent to previous methods in task accuracy and inference latency.
• Score: 50.33956216274694
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Finding optimal channel dimensions (i.e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints. Recent work in neural architecture search aims at automating the optimization of the DNN model implementation. However, existing neural architecture search methods for channel dimensions rely on fixed search spaces, which prevents achieving an efficient and fully automated solution. In this work, we propose a novel differentiable neural architecture search method with an efficient dynamic channel allocation algorithm to enable a flexible search space for channel dimensions. We show that the proposed framework is able to find DNN architectures that are equivalent to previous methods in task accuracy and inference latency for the CIFAR-10 dataset with an improvement of $1.3-1.7\times$ in GPU-hours and $1.5-1.7\times$ in the memory requirements during the architecture search stage. Moreover, the proposed frameworks do not require a well-engineered search space a priori, which is an important step towards fully automated design of DNN architectures.

Related papers

• PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization [3.460496851517031]
  PLiNIO is an open-source library implementing a comprehensive set of state-of-the-art DNN design automation techniques. We show that PLiNIO achieves up to 94.34% memory reduction for a 1% accuracy drop compared to a baseline architecture.
  arXiv  Detail & Related papers  (2023-07-18T07:11:14Z)
• DASS: Differentiable Architecture Search for Sparse neural networks [0.5735035463793009]
  We find that the architectures designed for dense networks by differentiable architecture search methods are ineffective when pruning mechanisms are applied to them. In this paper, we propose a new method to search for sparsity-friendly neural architectures. We do this by adding two new sparse operations to the search space and modifying the search objective.
  arXiv  Detail & Related papers  (2022-07-14T14:53:50Z)
• Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization [50.50023451369742]
  Pruning-as-Search (PaS) is an end-to-end channel pruning method to search out desired sub-network automatically and efficiently. Our proposed architecture outperforms prior arts by around $1.0%$ top-1 accuracy on ImageNet-1000 classification task.
  arXiv  Detail & Related papers  (2022-06-02T17:58:54Z)
• iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients [75.41173109807735]
  Differentiable ARchiTecture Search (DARTS) has recently become the mainstream of neural architecture search (NAS) We tackle the hypergradient computation in DARTS based on the implicit function theorem. We show that the architecture optimisation with the proposed method, named iDARTS, is expected to converge to a stationary point.
  arXiv  Detail & Related papers  (2021-06-21T00:44:11Z)
• AutoSpace: Neural Architecture Search with Less Human Interference [84.42680793945007]
  Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. We propose a novel differentiable evolutionary framework named AutoSpace, which evolves the search space to an optimal one. With the learned search space, the performance of recent NAS algorithms can be improved significantly compared with using previously manually designed spaces.
  arXiv  Detail & Related papers  (2021-03-22T13:28:56Z)
• Evolving Search Space for Neural Architecture Search [70.71153433676024]
  We present a Neural Search-space Evolution (NSE) scheme that amplifies the results from the previous effort by maintaining an optimized search space subset. We achieve 77.3% top-1 retrain accuracy on ImageNet with 333M FLOPs, which yielded a state-of-the-art performance. When the latency constraint is adopted, our result also performs better than the previous best-performing mobile models with a 77.9% Top-1 retrain accuracy.
  arXiv  Detail & Related papers  (2020-11-22T01:11:19Z)
• 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)
• Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation [4.595675084986132]
  The search space of neural architecture search (NAS) for convolutional neural network (CNN) is huge. We propose MoARR algorithm, which utilizes the existing research results and historical information to quickly find architectures that are both lightweight and accurate. Experimental results show that our MoARR can achieve a powerful and lightweight model (with 1.9% error rate and 2.3M parameters) on CIFAR-10 in 6 GPU hours.
  arXiv  Detail & Related papers  (2020-07-06T13:42:33Z)
• EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions [40.32848001349242]
  We propose a fully simultaneous, efficient differentiable DNN architecture and implementation co-search (EDD) methodology. We formulate the co-search problem by fusing search variables and hardware implementation variables into one solution space, and maximize both algorithm accuracy and hardware implementation quality.
  arXiv  Detail & Related papers  (2020-05-06T02:37:48Z)

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.