An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations

• URL: http://arxiv.org/abs/2505.16705v1
• Date: Thu, 22 May 2025 14:06:55 GMT
• Title: An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
• Authors: Seonghwan Park, Jueun Mun, Donghyun Oh, Namhoon Lee,
• Abstract summary: Concept bottleneck models (CBMs) ensure interpretability by decomposing predictions into human interpretable concepts.<n>Yet the annotations used for training CBMs that enable this transparency are often noisy.<n>Even moderate corruption simultaneously impairs prediction performance, interpretability, and the intervention effectiveness.
• Score: 4.72358438230281
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept bottleneck models (CBMs) ensure interpretability by decomposing predictions into human interpretable concepts. Yet the annotations used for training CBMs that enable this transparency are often noisy, and the impact of such corruption is not well understood. In this study, we present the first systematic study of noise in CBMs and show that even moderate corruption simultaneously impairs prediction performance, interpretability, and the intervention effectiveness. Our analysis identifies a susceptible subset of concepts whose accuracy declines far more than the average gap between noisy and clean supervision and whose corruption accounts for most performance loss. To mitigate this vulnerability we propose a two-stage framework. During training, sharpness-aware minimization stabilizes the learning of noise-sensitive concepts. During inference, where clean labels are unavailable, we rank concepts by predictive entropy and correct only the most uncertain ones, using uncertainty as a proxy for susceptibility. Theoretical analysis and extensive ablations elucidate why sharpness-aware training confers robustness and why uncertainty reliably identifies susceptible concepts, providing a principled basis that preserves both interpretability and resilience in the presence of noise.

Related papers

• TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation [11.334867025651233]
  We propose TULiP, a theoretically-driven uncertainty estimator for OOD detection.<n>Our approach considers a hypothetical perturbation applied to the network before convergence.<n>Our method exhibits state-of-the-art performance, particularly for near-distribution samples.
  arXiv  Detail & Related papers  (2025-05-22T17:16:41Z)
• All You Need for Counterfactual Explainability Is Principled and Reliable Estimate of Aleatoric and Epistemic Uncertainty [27.344785490275864]
  We argue that transparency research overlooks many foundational concepts of artificial intelligence.<n>Inherently transparent models can benefit from human-centred explanatory insights.<n>At a higher level, integrating artificial intelligence fundamentals into transparency research promises to yield more reliable, robust and understandable predictive models.
  arXiv  Detail & Related papers  (2025-02-24T09:38:31Z)
• Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching [61.73532883992135]
  We propose a new uncertainty-aware stereo matching framework.<n>We adopt Bayes risk as the measurement of uncertainty and use it to separately estimate data and model uncertainty.
  arXiv  Detail & Related papers  (2024-12-24T23:28:20Z)
• Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework [54.40508478482667]
  We present a comprehensive framework to disentangle, quantify, and mitigate uncertainty in perception and plan generation.<n>We propose methods tailored to the unique properties of perception and decision-making.<n>We show that our uncertainty disentanglement framework reduces variability by up to 40% and enhances task success rates by 5% compared to baselines.
  arXiv  Detail & Related papers  (2024-11-03T17:32:00Z)
• Integrating Uncertainty into Neural Network-based Speech Enhancement [27.868722093985006]
  Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of reliability. We study the benefits of modeling uncertainty in clean speech estimation.
  arXiv  Detail & Related papers  (2023-05-15T15:55:12Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)
• Elucidating Noisy Data via Uncertainty-Aware Robust Learning [9.711326718689495]
  Our proposed method can learn the clean target distribution from a dirty dataset. We leverage a mixture-of-experts model that can distinguish two different types of predictive uncertainty. We present a novel validation scheme for evaluating the performance of the corruption pattern estimation.
  arXiv  Detail & Related papers  (2021-11-02T14:44:50Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)
• Getting a CLUE: A Method for Explaining Uncertainty Estimates [30.367995696223726]
  We propose a novel method for interpreting uncertainty estimates from differentiable probabilistic models. Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold.
  arXiv  Detail & Related papers  (2020-06-11T21:53:15Z)

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.