Understanding the effect of sparsity on neural networks robustness

• URL: http://arxiv.org/abs/2206.10915v1
• Date: Wed, 22 Jun 2022 08:51:40 GMT
• Title: Understanding the effect of sparsity on neural networks robustness
• Authors: Lukas Timpl, Rahim Entezari, Hanie Sedghi, Behnam Neyshabur, Olga Saukh
• Abstract summary: This paper examines the impact of static sparsity on the robustness of a trained network to weight perturbations, data corruption, and adversarial examples. We show that, up to a certain sparsity achieved by increasing network width and depth while keeping the network capacity fixed, sparsified networks consistently match and often outperform their initially dense versions.
• Score: 32.15505923976003
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper examines the impact of static sparsity on the robustness of a trained network to weight perturbations, data corruption, and adversarial examples. We show that, up to a certain sparsity achieved by increasing network width and depth while keeping the network capacity fixed, sparsified networks consistently match and often outperform their initially dense versions. Robustness and accuracy decline simultaneously for very high sparsity due to loose connectivity between network layers. Our findings show that a rapid robustness drop caused by network compression observed in the literature is due to a reduced network capacity rather than sparsity.

Related papers

• Beyond Pruning Criteria: The Dominant Role of Fine-Tuning and Adaptive Ratios in Neural Network Robustness [7.742297876120561]
  Deep neural networks (DNNs) excel in tasks like image recognition and natural language processing. Traditional pruning methods compromise the network's ability to withstand subtle perturbations. This paper challenges the conventional emphasis on weight importance scoring as the primary determinant of a pruned network's performance.
  arXiv  Detail & Related papers  (2024-10-19T18:35:52Z)
• Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks [54.565579874913816]
  Neural networks demonstrate inherent vulnerability to small, non-random perturbations, emerging as adversarial attacks. A mathematical congruence manifests between this mechanism and the quantum physics' uncertainty principle, casting light on a hitherto unanticipated interdisciplinarity.
  arXiv  Detail & Related papers  (2024-02-16T02:11:27Z)
• Robustness to distribution shifts of compressed networks for edge devices [6.606005367624169]
  It is important to investigate the robustness of compressed networks in two types of data distribution shifts: domain shifts and adversarial perturbations. In this study, we discover that compressed models are less robust to distribution shifts than their original networks. compact networks obtained by knowledge distillation are much more robust to distribution shifts than pruned networks.
  arXiv  Detail & Related papers  (2024-01-22T15:00:32Z)
• Improving Corruption and Adversarial Robustness by Enhancing Weak Subnets [91.9346332103637]
  We propose a novel robust training method which explicitly identifies and enhances weaks during training to improve robustness. Specifically, we develop a search algorithm to find particularly weaks and propose to explicitly strengthen them via knowledge distillation from the full network. We show that our EWS greatly improves the robustness against corrupted images as well as the accuracy on clean data.
  arXiv  Detail & Related papers  (2022-01-30T09:36:19Z)
• Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks [9.554646174100123]
  We show that the dynamics of the gradient descent training algorithm has a key role in obtaining compressible networks. We prove that the networks are guaranteed to be '$ell_p$-compressible', and the compression errors of different pruning techniques become arbitrarily small as the network size increases.
  arXiv  Detail & Related papers  (2021-06-07T17:02:59Z)
• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks [78.47459801017959]
  Sparsity can reduce the memory footprint of regular networks to fit mobile devices. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice.
  arXiv  Detail & Related papers  (2021-01-31T22:48:50Z)
• Attribution Preservation in Network Compression for Reliable Network Interpretation [81.84564694303397]
  Neural networks embedded in safety-sensitive applications rely on input attribution for hindsight analysis and network compression to reduce its size for edge-computing. We show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions. This phenomenon arises due to the fact that conventional network compression methods only preserve the predictions of the network while ignoring the quality of the attributions.
  arXiv  Detail & Related papers  (2020-10-28T16:02:31Z)
• Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer [61.85316480370141]
  We study data-free quantization and pruning by transferring knowledge from trained large networks to compact networks. Our data-free compact networks achieve competitive accuracy to networks trained and fine-tuned with training data.
  arXiv  Detail & Related papers  (2020-10-14T18:02:55Z)
• Achieving Adversarial Robustness via Sparsity [33.11581532788394]
  We prove that the sparsity of network weights is closely associated with model robustness. We propose a novel adversarial training method called inverse weights inheritance.
  arXiv  Detail & Related papers  (2020-09-11T13:15:43Z)
• Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness [97.67477497115163]
  We use mode connectivity to study the adversarial robustness of deep neural networks. Our experiments cover various types of adversarial attacks applied to different network architectures and datasets. Our results suggest that mode connectivity offers a holistic tool and practical means for evaluating and improving adversarial robustness.
  arXiv  Detail & Related papers  (2020-04-30T19:12:50Z)

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.