Adversarial Information Bottleneck

• URL: http://arxiv.org/abs/2103.00381v2
• Date: Wed, 3 Mar 2021 03:42:00 GMT
• Title: Adversarial Information Bottleneck
• Authors: Penglong Zhai and Shihua Zhang
• Abstract summary: The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction. Previous methods attempted to optimize the IB principle by introducing random noise into learning the representation. We propose an adversarial information bottleneck (AIB) method without any explicit assumptions about the underlying distribution of the representations.
• Score: 2.66512000865131
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a trade-off hyperparameter. How to optimize the IB principle for better robustness and figure out the effects of compression through the trade-off hyperparameter are two challenging problems. Previous methods attempted to optimize the IB principle by introducing random noise into learning the representation and achieved state-of-the-art performance in the nuisance information compression and semantic information extraction. However, their performance on resisting adversarial perturbations is far less impressive. To this end, we propose an adversarial information bottleneck (AIB) method without any explicit assumptions about the underlying distribution of the representations, which can be optimized effectively by solving a Min-Max optimization problem. Numerical experiments on synthetic and real-world datasets demonstrate its effectiveness on learning more invariant representations and mitigating adversarial perturbations compared to several competing IB methods. In addition, we analyse the adversarial robustness of diverse IB methods contrasting with their IB curves, and reveal that IB models with the hyperparameter $\beta$ corresponding to the knee point in the IB curve achieve the best trade-off between compression and prediction, and has best robustness against various attacks.

Related papers

• The Common Stability Mechanism behind most Self-Supervised Learning Approaches [64.40701218561921]
  We provide a framework to explain the stability mechanism of different self-supervised learning techniques. We discuss the working mechanism of contrastive techniques like SimCLR, non-contrastive techniques like BYOL, SWAV, SimSiam, Barlow Twins, and DINO. We formulate different hypotheses and test them using the Imagenet100 dataset.
  arXiv  Detail & Related papers  (2024-02-22T20:36:24Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• Disentangled Representation Learning with Transmitted Information Bottleneck [57.22757813140418]
  We present textbfDisTIB (textbfTransmitted textbfInformation textbfBottleneck for textbfDisd representation learning), a novel objective that navigates the balance between information compression and preservation.
  arXiv  Detail & Related papers  (2023-11-03T03:18:40Z)
• The Information Bottleneck's Ordinary Differential Equation: First-Order Root-Tracking for the IB [0.0]
  The Information Bottleneck (IB) is a method of lossy compression of relevant information. We exploit the dynamics underlying the IB's optimal tradeoff curve. We translate an understanding of IB bifurcations into a surprisingly accurate numerical algorithm.
  arXiv  Detail & Related papers  (2023-06-16T12:02:19Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• Variational Distillation for Multi-View Learning [104.17551354374821]
  We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
  arXiv  Detail & Related papers  (2022-06-20T03:09:46Z)
• Pseudo-Spherical Contrastive Divergence [119.28384561517292]
  We propose pseudo-spherical contrastive divergence (PS-CD) to generalize maximum learning likelihood of energy-based models. PS-CD avoids the intractable partition function and provides a generalized family of learning objectives.
  arXiv  Detail & Related papers  (2021-11-01T09:17:15Z)
• Perturbation Theory for the Information Bottleneck [6.117084972237769]
  Information bottleneck (IB) method formalizes extracting relevant information from data. nonlinearity of the IB problem makes it computationally expensive and analytically intractable in general. We derive a perturbation theory for the IB method and report the first complete characterization of the learning onset.
  arXiv  Detail & Related papers  (2021-05-28T16:59:01Z)
• Disentangled Information Bottleneck [22.587164077221917]
  We introduce Disentangled Information Bottleneck (DisenIB) that is consistent on compressing source maximally without target prediction performance loss. Our method is consistent on maximum compression, and performs well in terms of generalization, robustness to adversarial attack, out-of-distribution detection, and supervised disentangling.
  arXiv  Detail & Related papers  (2020-12-14T09:44:07Z)

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.