DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

• URL: http://arxiv.org/abs/2307.02094v1
• Date: Wed, 5 Jul 2023 08:11:40 GMT
• Title: DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications
• Authors: Adam Ivankay, Mattia Rigotti, Pascal Frossard
• Abstract summary: We show how to adapt attribution robustness estimation methods to a given domain, so as to take into account domain-specific plausibility. Next, we provide two methods, adversarial training and FAR training, to mitigate the brittleness characterized by DARE. Finally, we empirically validate our methods with extensive experiments on three established biomedical benchmarks.
• Score: 54.93807822347193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several methods have been introduced to provide insight into the inference process of deep neural networks. However, most of these explainability methods have been shown to be brittle in the face of adversarial perturbations of their inputs in the image and generic textual domain. In this work we show that this phenomenon extends to specific and important high stakes domains like biomedical datasets. In particular, we observe that the robustness of explanations should be characterized in terms of the accuracy of the explanation in linking a model's inputs and its decisions - faithfulness - and its relevance from the perspective of domain experts - plausibility. This is crucial to prevent explanations that are inaccurate but still look convincing in the context of the domain at hand. To this end, we show how to adapt current attribution robustness estimation methods to a given domain, so as to take into account domain-specific plausibility. This results in our DomainAdaptiveAREstimator (DARE) attribution robustness estimator, allowing us to properly characterize the domain-specific robustness of faithful explanations. Next, we provide two methods, adversarial training and FAR training, to mitigate the brittleness characterized by DARE, allowing us to train networks that display robust attributions. Finally, we empirically validate our methods with extensive experiments on three established biomedical benchmarks.

Related papers

• Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks [9.999199798941424]
  We propose a Bayesian neural architecture that disentangles the learning of the the data distribution from the inference process mechanisms. We show theoretically and experimentally that our model approximates reasoning under causal interventions.
  arXiv  Detail & Related papers  (2024-10-08T20:38:05Z)
• Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance [29.016425469068587]
  We propose a novel framework, Unfold and Conquer Guidance (UCAG), which enhances the explainability of the network decision. UCAG sequentially complies with the confidence of slices of the image, leading to providing an abundant and clear interpretation. We conduct numerous evaluations to validate the performance in several metrics.
  arXiv  Detail & Related papers  (2023-12-21T03:43:19Z)
• Generalizability of Adversarial Robustness Under Distribution Shifts [57.767152566761304]
  We take a first step towards investigating the interplay between empirical and certified adversarial robustness on one hand and domain generalization on another. We train robust models on multiple domains and evaluate their accuracy and robustness on an unseen domain. We extend our study to cover a real-world medical application, in which adversarial augmentation significantly boosts the generalization of robustness with minimal effect on clean data accuracy.
  arXiv  Detail & Related papers  (2022-09-29T18:25:48Z)
• Robustness in Deep Learning for Computer Vision: Mind the gap? [13.576376492050185]
  We identify, analyze, and summarize current definitions and progress towards non-adversarial robustness in deep learning for computer vision. We find that this area of research has received disproportionately little attention relative to adversarial machine learning.
  arXiv  Detail & Related papers  (2021-12-01T16:42:38Z)
• On the Importance of Regularisation & Auxiliary Information in OOD Detection [9.340611077939828]
  This deficiency demonstrates a fundamental flaw indicating that neural networks often overfit on spurious correlations. We present two novel objectives that improve the ability of a network to detect out-of-distribution samples.
  arXiv  Detail & Related papers  (2021-07-15T18:57:10Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty [111.22588110362705]
  Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference. We derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network.
  arXiv  Detail & Related papers  (2021-05-09T21:33:27Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)
• How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks [19.648814035399013]
  Explainable AI (XAI) aims to provide interpretations for predictions made by learning machines, such as deep neural networks. We propose a new framework that allows to convert any arbitrary explanation method for neural networks into an explanation method for Bayesian neural networks. We demonstrate the effectiveness and usefulness of our approach extensively in various experiments.
  arXiv  Detail & Related papers  (2020-06-16T08:54:42Z)
• Hold me tight! Influence of discriminative features on deep network boundaries [63.627760598441796]
  We propose a new perspective that relates dataset features to the distance of samples to the decision boundary. This enables us to carefully tweak the position of the training samples and measure the induced changes on the boundaries of CNNs trained on large-scale vision datasets.
  arXiv  Detail & Related papers  (2020-02-15T09:29:36Z)

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.