$α$-TCAV: A Unified Framework for Testing with Concept Activation Vectors

• URL: http://arxiv.org/abs/2605.15688v1
• Date: Fri, 15 May 2026 07:22:59 GMT
• Title: $α$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
• Abstract summary: Concept Vectors (CAVs) are a tool for concept-based explainability in deep learning.<n>We analyze the nature of CAVs and the Activation Testing with CAVs (TCAV) method.<n>We introduce $$-TCAV, a generalized framework that replaces the indicator with a parameterized smooth function.
• Score: 55.54306267760148
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Concept Activation Vectors (CAVs) are a fundamental tool for concept-based explainability in deep learning, yet their practical utility is limited by statistical instability. We analyze the stochastic nature of CAVs and the Testing with CAVs (TCAV) method, deriving the distributions of major CAV classes including PatternCAV, FastCAV, and ridge regression-based CAVs. We then identify a fundamental flaw in the standard TCAV score: its reliance on a discontinuous indicator function induces non-decaying variance in critical regimes. To address this, we introduce $α$-TCAV, a generalized framework that replaces the indicator with a parameterized smooth function, yielding a unified probabilistic formulation that subsumes both TCAV and Multi-TCAV. We characterize the induced distributions of sensitivity scores and different TCAV variants, showing that established state-of-the-art choices lack theoretical justification. We provide principled guidance on tuning the parameter in $α$-TCAV -- either to imitate Multi-TCAV at substantially lower computational cost, or to obtain a calibrated Bayes-optimal probabilistic measure of a concept's influence. Finally, our analysis yields practical recommendations that challenge established routines: most notably, allocating the full sampling budget to a single CAV rather than splitting it across several.

Related papers

• E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability [6.496864934809427]
  TCAV (Testing with Concept Activation Vectors) is an interpretability method.<n> TCAV suffers from significant computational overhead, inter-layer disagreement of TCAV scores, and statistical instability.<n>E-TCAV is a framework for efficient approximation of TCAV scores.
  arXiv  Detail & Related papers  (2026-05-11T09:25:41Z)
• TPV: Parameter Perturbations Through the Lens of Test Prediction Variance [1.9443009938188445]
  Test prediction variance (TPV) is the first-order sensitivity of model outputs to perturbations around a trained solution.<n>TPV is a fully label-free object whose trace form separates the geometry of the trained model from the specific perturbation mechanism.
  arXiv  Detail & Related papers  (2025-12-11T20:04:33Z)
• GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability [41.6338086518055]
  Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts.<n>When computed independently at different layers, CAVs often exhibit inconsistencies, making cross-layer comparisons unreliable.<n>We propose the Global Concept Activation Vector (GCAV), a novel framework that unifies CAVs into a single, semantically consistent representation.
  arXiv  Detail & Related papers  (2025-08-28T20:29:05Z)
• One Sample is Enough to Make Conformal Prediction Robust [53.78604391939934]
  We show that conformal prediction attains some robustness even with a forward pass on a single randomly perturbed input.<n>Our approach returns robust sets with smaller average set size compared to SOTA methods which use many (e.g. around 100) passes per input.
  arXiv  Detail & Related papers  (2025-06-19T19:14:25Z)
• Probabilistic Variational Contrastive Learning [8.23660331371415]
  We propose a decoder-free framework that maximizes the evidence lower bound (ELBO)<n>We model the approximate posterior $q_theta(z|x)$ as a projected normal distribution, enabling the sampling of probabilistic embeddings.
  arXiv  Detail & Related papers  (2025-06-11T20:26:07Z)
• Conformal Risk Minimization with Variance Reduction [37.74931189657469]
  Conformal prediction (CP) is a distribution-free framework for achieving probabilistic guarantees on black-box models.<n>Recent research efforts have focused on optimizing CP efficiency during training.<n>We formalize this concept as the problem of conformal risk minimization.
  arXiv  Detail & Related papers  (2024-11-03T21:48:15Z)
• Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence [13.618809162030486]
  Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space.<n>In this paper we show that such a separability-oriented leads to solutions, which may diverge from the actual goal of precisely modeling the concept direction.<n>We introduce pattern-based CAVs, solely focussing on concept signals, thereby providing more accurate concept directions.
  arXiv  Detail & Related papers  (2022-02-07T19:40:20Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks [58.29502185344086]
  In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks. It is important to provide provable guarantees for deep learning models against semantically meaningful input transformations. We propose a new universal probabilistic certification approach based on Chernoff-Cramer bounds.
  arXiv  Detail & Related papers  (2021-09-22T12:46:04Z)
• 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)
• Evaluating probabilistic classifiers: Reliability diagrams and score decompositions revisited [68.8204255655161]
  We introduce the CORP approach, which generates provably statistically Consistent, Optimally binned, and Reproducible reliability diagrams in an automated way. Corpor is based on non-parametric isotonic regression and implemented via the Pool-adjacent-violators (PAV) algorithm.
  arXiv  Detail & Related papers  (2020-08-07T08:22:26Z)

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.