On the Robustness of Removal-Based Feature Attributions
- URL: http://arxiv.org/abs/2306.07462v2
- Date: Mon, 30 Oct 2023 23:08:42 GMT
- Title: On the Robustness of Removal-Based Feature Attributions
- Authors: Chris Lin, Ian Covert, Su-In Lee
- Abstract summary: We theoretically characterize the properties of robustness of removal-based feature attributions.
Specifically, we provide a unified analysis of such methods and derive upper bounds for the difference between intact and perturbed attributions.
Our results on synthetic and real-world data validate our theoretical results and demonstrate their practical implications.
- Score: 17.679374058425346
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: To explain predictions made by complex machine learning models, many feature
attribution methods have been developed that assign importance scores to input
features. Some recent work challenges the robustness of these methods by
showing that they are sensitive to input and model perturbations, while other
work addresses this issue by proposing robust attribution methods. However,
previous work on attribution robustness has focused primarily on gradient-based
feature attributions, whereas the robustness of removal-based attribution
methods is not currently well understood. To bridge this gap, we theoretically
characterize the robustness properties of removal-based feature attributions.
Specifically, we provide a unified analysis of such methods and derive upper
bounds for the difference between intact and perturbed attributions, under
settings of both input and model perturbations. Our empirical results on
synthetic and real-world data validate our theoretical results and demonstrate
their practical implications, including the ability to increase attribution
robustness by improving the model's Lipschitz regularity.
Related papers
- Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance [61.06245197347139]
We propose a novel approach to explain the behavior of a black-box model under feature shifts.
We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation.
arXiv Detail & Related papers (2024-08-24T18:28:19Z) - Improving Adversarial Robustness via Feature Pattern Consistency Constraint [42.50500608175905]
Convolutional Neural Networks (CNNs) are well-known for their vulnerability to adversarial attacks, posing significant security concerns.
Most existing methods either focus on learning from adversarial perturbations, leading to overfitting to the adversarial examples, or aim to eliminate such perturbations during inference.
We introduce a novel and effective Feature Pattern Consistency Constraint (FPCC) method to reinforce the latent feature's capacity to maintain the correct feature pattern.
arXiv Detail & Related papers (2024-06-13T05:38:30Z) - Identifiable Latent Neural Causal Models [82.14087963690561]
Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data.
We determine the types of distribution shifts that do contribute to the identifiability of causal representations.
We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
arXiv Detail & Related papers (2024-03-23T04:13:55Z) - 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) - Consistent Explanations in the Face of Model Indeterminacy via
Ensembling [12.661530681518899]
This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy.
We introduce ensemble methods to enhance the consistency of the explanations provided in these scenarios.
Our findings highlight the importance of considering model indeterminacy when interpreting explanations.
arXiv Detail & Related papers (2023-06-09T18:45:43Z) - Causal Analysis for Robust Interpretability of Neural Networks [0.2519906683279152]
We develop a robust interventional-based method to capture cause-effect mechanisms in pre-trained neural networks.
We apply our method to vision models trained on classification tasks.
arXiv Detail & Related papers (2023-05-15T18:37:24Z) - Enhancing Model Robustness and Fairness with Causality: A Regularization
Approach [15.981724441808147]
Recent work has raised concerns on the risk of spurious correlations and unintended biases in machine learning models.
We propose a simple and intuitive regularization approach to integrate causal knowledge during model training.
We build a predictive model that relies more on causal features and less on non-causal features.
arXiv Detail & Related papers (2021-10-03T02:49:33Z) - Estimation of Bivariate Structural Causal Models by Variational Gaussian
Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
Causal mechanisms can be described by structural causal models.
One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
arXiv Detail & Related papers (2021-09-06T14:52:58Z) - Accurate and Robust Feature Importance Estimation under Distribution
Shifts [49.58991359544005]
PRoFILE is a novel feature importance estimation method.
We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
arXiv Detail & Related papers (2020-09-30T05:29:01Z) - Accounting for Unobserved Confounding in Domain Generalization [107.0464488046289]
This paper investigates the problem of learning robust, generalizable prediction models from a combination of datasets.
Part of the challenge of learning robust models lies in the influence of unobserved confounders.
We demonstrate the empirical performance of our approach on healthcare data from different modalities.
arXiv Detail & Related papers (2020-07-21T08:18:06Z)
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.