DεpS: Delayed ε-Shrinking for Faster Once-For-All Training

• URL: http://arxiv.org/abs/2407.06167v1
• Date: Mon, 8 Jul 2024 17:45:40 GMT
• Title: DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
• Authors: Aditya Annavajjala, Alind Khare, Animesh Agrawal, Igor Fedorov, Hugo Latapie, Myungjin Lee, Alexey Tumanov,
• Abstract summary: CNNs are increasingly deployed across different hardware, dynamic environments, and low-power embedded devices. Once-for-all training has emerged as a scalable approach that jointly co-trains many models (subnets) at once with a constant training cost. We propose Delayed $epsilon$-Shrinking (D$epsilon$pS) that starts the process of shrinking the full model when it is partially trained.
• Score: 8.199430861588919
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: CNNs are increasingly deployed across different hardware, dynamic environments, and low-power embedded devices. This has led to the design and training of CNN architectures with the goal of maximizing accuracy subject to such variable deployment constraints. As the number of deployment scenarios grows, there is a need to find scalable solutions to design and train specialized CNNs. Once-for-all training has emerged as a scalable approach that jointly co-trains many models (subnets) at once with a constant training cost and finds specialized CNNs later. The scalability is achieved by training the full model and simultaneously reducing it to smaller subnets that share model weights (weight-shared shrinking). However, existing once-for-all training approaches incur huge training costs reaching 1200 GPU hours. We argue this is because they either start the process of shrinking the full model too early or too late. Hence, we propose Delayed $\epsilon$-Shrinking (D$\epsilon$pS) that starts the process of shrinking the full model when it is partially trained (~50%) which leads to training cost improvement and better in-place knowledge distillation to smaller models. The proposed approach also consists of novel heuristics that dynamically adjust subnet learning rates incrementally (E), leading to improved weight-shared knowledge distillation from larger to smaller subnets as well. As a result, DEpS outperforms state-of-the-art once-for-all training techniques across different datasets including CIFAR10/100, ImageNet-100, and ImageNet-1k on accuracy and cost. It achieves 1.83% higher ImageNet-1k top1 accuracy or the same accuracy with 1.3x reduction in FLOPs and 2.5x drop in training cost (GPU*hrs)

Related papers

• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• Effective pruning of web-scale datasets based on complexity of concept clusters [48.125618324485195]
  We present a method for pruning large-scale multimodal datasets for training CLIP-style models on ImageNet. We find that training on a smaller set of high-quality data can lead to higher performance with significantly lower training costs. We achieve a new state-of-the-art Imagehttps://info.arxiv.org/help/prep#commentsNet zero-shot accuracy and a competitive average zero-shot accuracy on 38 evaluation tasks.
  arXiv  Detail & Related papers  (2024-01-09T14:32:24Z)
• Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models [0.0]
  We demonstrate how an efficient deep convolution network can be built in a phased manner by sequentially reducing the number of training parameters. We achieved a SOTA accuracy of 99.2% on MNIST data with just 1500 parameters and an accuracy of 86.01% with just over 140K parameters on the CIFAR-10 dataset.
  arXiv  Detail & Related papers  (2022-05-23T13:51:06Z)
• Structured Pruning is All You Need for Pruning CNNs at Initialization [38.88730369884401]
  Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs) We propose PreCropping, a structured hardware-efficient model compression scheme. Compared to weight pruning, the proposed scheme is regular and dense in both storage and computation without sacrificing accuracy.
  arXiv  Detail & Related papers  (2022-03-04T19:54:31Z)
• ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training [65.68511423300812]
  We propose ProgFed, a progressive training framework for efficient and effective federated learning. ProgFed inherently reduces computation and two-way communication costs while maintaining the strong performance of the final models. Our results show that ProgFed converges at the same rate as standard training on full models.
  arXiv  Detail & Related papers  (2021-10-11T14:45:00Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• Simultaneous Training of Partially Masked Neural Networks [67.19481956584465]
  We show that it is possible to train neural networks in such a way that a predefined 'core' subnetwork can be split-off from the trained full network with remarkable good performance. We show that training a Transformer with a low-rank core gives a low-rank model with superior performance than when training the low-rank model alone.
  arXiv  Detail & Related papers  (2021-06-16T15:57:51Z)
• EfficientNetV2: Smaller Models and Faster Training [91.77432224225221]
  This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. We use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller.
  arXiv  Detail & Related papers  (2021-04-01T07:08:36Z)
• ClickTrain: Efficient and Accurate End-to-End Deep Learning Training via Fine-Grained Architecture-Preserving Pruning [35.22893238058557]
  Convolutional neural networks (CNNs) are becoming increasingly deeper, wider, and non-linear. We propose ClickTrain: an efficient end-to-end training and pruning framework for CNNs.
  arXiv  Detail & Related papers  (2020-11-20T01:46:56Z)

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.