Unifying Synergies between Self-supervised Learning and Dynamic Computation

• URL: http://arxiv.org/abs/2301.09164v3
• Date: Sat, 9 Sep 2023 20:43:13 GMT
• Title: Unifying Synergies between Self-supervised Learning and Dynamic Computation
• Authors: Tarun Krishna, Ayush K Rai, Alexandru Drimbarean, Eric Arazo, Paul Albert, Alan F Smeaton, Kevin McGuinness, Noel E O'Connor
• Abstract summary: We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
• Score: 53.66628188936682
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computationally expensive training strategies make self-supervised learning (SSL) impractical for resource constrained industrial settings. Techniques like knowledge distillation (KD), dynamic computation (DC), and pruning are often used to obtain a lightweightmodel, which usually involves multiple epochs of fine-tuning (or distilling steps) of a large pre-trained model, making it more computationally challenging. In this work we present a novel perspective on the interplay between SSL and DC paradigms. In particular, we show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting without any additional fine-tuning or pruning steps. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off and therefore yields a generic and multi-purpose architecture for application specific industrial settings. Extensive experiments on several image classification benchmarks including CIFAR-10/100, STL-10 and ImageNet-100, demonstrate that the proposed training strategy provides a dense and corresponding gated sub-network that achieves on-par performance compared with the vanilla self-supervised setting, but at a significant reduction in computation in terms of FLOPs, under a range of target budgets (td ).

Related papers

• Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identification [3.0398616939692777]
  Techniques like adversarial learning, contrastive learning, diffusion denoising learning, and ordinary reconstruction learning have become standard. The study aims to elucidate the advantages of pre-training techniques and fine-tuning strategies to enhance the learning process of neural networks.
  arXiv  Detail & Related papers  (2024-05-29T15:44:51Z)
• LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks [52.46420522934253]
  We introduce LoRA-Ensemble, a parameter-efficient deep ensemble method for self-attention networks. By employing a single pre-trained self-attention network with weights shared across all members, we train member-specific low-rank matrices for the attention projections. Our method exhibits superior calibration compared to explicit ensembles and achieves similar or better accuracy across various prediction tasks and datasets.
  arXiv  Detail & Related papers  (2024-05-23T11:10:32Z)
• 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)
• When Computing Power Network Meets Distributed Machine Learning: An Efficient Federated Split Learning Framework [6.871107511111629]
  CPN-FedSL is a Federated Split Learning (FedSL) framework over Computing Power Network (CPN) We build a dedicated model to capture the basic settings and learning characteristics (e.g., latency, flow, convergence)
  arXiv  Detail & Related papers  (2023-05-22T12:36:52Z)
• Training Spiking Neural Networks with Local Tandem Learning [96.32026780517097]
  Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient than their predecessors. In this paper, we put forward a generalized learning rule, termed Local Tandem Learning (LTL) We demonstrate rapid network convergence within five training epochs on the CIFAR-10 dataset while having low computational complexity.
  arXiv  Detail & Related papers  (2022-10-10T10:05:00Z)
• Effective Self-supervised Pre-training on Low-compute Networks without Distillation [6.530011859253459]
  Reported performance of self-supervised learning has trailed behind standard supervised pre-training by a large margin. Most prior works attribute this poor performance to the capacity bottleneck of the low-compute networks. We take a closer at what are the detrimental factors causing the practical limitations, and whether they are intrinsic to the self-supervised low-compute setting.
  arXiv  Detail & Related papers  (2022-10-06T10:38:07Z)
• DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference [85.02494022662505]
  DANCE is an automated simultaneous data-network co-optimization for efficient segmentation model training and inference. It integrates automated data slimming which adaptively downsamples/drops input images and controls their corresponding contribution to the training loss guided by the images' spatial complexity. Experiments and ablating studies demonstrate that DANCE can achieve "all-win" towards efficient segmentation.
  arXiv  Detail & Related papers  (2021-07-16T04:58:58Z)
• Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning [88.17413955380262]
  Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy. We introduce a novel method called Multi-Exit Curriculum Learning that utilizes curriculum learning. Our method consistently improves the accuracy of early exits compared to the standard training approach.
  arXiv  Detail & Related papers  (2021-04-21T11:12:35Z)
• Embedded Knowledge Distillation in Depth-level Dynamic Neural Network [8.207403859762044]
  We propose an elegant Depth-level Dynamic Neural Network (DDNN) integrated different-depth sub-nets of similar architectures. In this article, we design the Embedded-Knowledge-Distillation (EKD) training mechanism for the DDNN to implement semantic knowledge transfer from the teacher (full) net to multiple sub-nets. Experiments on CIFAR-10, CIFAR-100, and ImageNet datasets demonstrate that sub-nets in DDNN with EKD training achieves better performance than the depth-level pruning or individually training.
  arXiv  Detail & Related papers  (2021-03-01T06:35:31Z)

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.