Attribution Preservation in Network Compression for Reliable Network Interpretation

• URL: http://arxiv.org/abs/2010.15054v1
• Date: Wed, 28 Oct 2020 16:02:31 GMT
• Title: Attribution Preservation in Network Compression for Reliable Network Interpretation
• Authors: Geondo Park, June Yong Yang, Sung Ju Hwang, Eunho Yang
• Abstract summary: 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.
• Score: 81.84564694303397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing. In this paper, we show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions, which could lead to dire consequences for mission-critical applications. 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. To combat the attribution inconsistency problem, we present a framework that can preserve the attributions while compressing a network. By employing the Weighted Collapsed Attribution Matching regularizer, we match the attribution maps of the network being compressed to its pre-compression former self. We demonstrate the effectiveness of our algorithm both quantitatively and qualitatively on diverse compression methods.

Related papers

• 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)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• Understanding the effect of sparsity on neural networks robustness [32.15505923976003]
  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.
  arXiv  Detail & Related papers  (2022-06-22T08:51:40Z)
• A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation [37.525277809849776]
  The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. We use sparsity-sensitive $ell_q$-norm to characterize compressibility and provide a relationship between soft sparsity of the weights in the network and the degree of compression. We also develop adaptive algorithms for pruning each neuron in the network informed by our theory.
  arXiv  Detail & Related papers  (2022-06-11T20:10:35Z)
• Fast Conditional Network Compression Using Bayesian HyperNetworks [54.06346724244786]
  We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts. Our methods can quickly generate compressed networks with significantly smaller sizes than baseline methods.
  arXiv  Detail & Related papers  (2022-05-13T00:28:35Z)
• On the Compression of Neural Networks Using $\ell_0$-Norm Regularization and Weight Pruning [0.9821874476902968]
  The present paper is dedicated to the development of a novel compression scheme for neural networks. A new form of regularization is firstly developed, which is capable of inducing strong sparseness in the network during training. The proposed compression scheme also involves the use of $ell$-norm regularization to avoid overfitting as well as fine tuning to improve the performance of the pruned network.
  arXiv  Detail & Related papers  (2021-09-10T19:19:42Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• 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)
• Optimal Network Compression [0.0]
  This paper introduces a formulation of the optimal network compression problem for financial systems. We focus on objective functions generated by systemic risk measures under shocks to the financial network. We conclude by studying the optimal compression problem for specific networks.
  arXiv  Detail & Related papers  (2020-08-20T02:11:23Z)
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle [117.95823660228537]
  We propose a novel structured sparsification method for efficient network compression. The proposed method automatically induces structured sparsity on the convolutional weights. We also address the problem of inter-group communication with a learnable channel shuffle mechanism.
  arXiv  Detail & Related papers  (2020-02-19T12:03:10Z)

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.