Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models

• URL: http://arxiv.org/abs/2510.05670v2
• Date: Thu, 16 Oct 2025 11:37:20 GMT
• Title: Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
• Authors: David Debot, Giuseppe Marra,
• Abstract summary: Concept Bottleneck Models (CBNMs) provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts.<n>This constraint also restricts information flow and often results in reduced predictive accuracy.<n> Concept Sidechannel Models (CSMs) address this limitation by introducing a sidechannel that bypasses the bottleneck and carry additional task-relevant information.
• Score: 18.731133116993707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts information flow and often results in reduced predictive accuracy. Concept Sidechannel Models (CSMs) address this limitation by introducing a sidechannel that bypasses the bottleneck and carry additional task-relevant information. While this improves accuracy, it simultaneously compromises interpretability, as predictions may rely on uninterpretable representations transmitted through sidechannels. Currently, there exists no principled technique to control this fundamental trade-off. In this paper, we close this gap. First, we present a unified probabilistic concept sidechannel meta-model that subsumes existing CSMs as special cases. Building on this framework, we introduce the Sidechannel Independence Score (SIS), a metric that quantifies a CSM's reliance on its sidechannel by contrasting predictions made with and without sidechannel information. We propose SIS regularization, which explicitly penalizes sidechannel reliance to improve interpretability. Finally, we analyze how the expressivity of the predictor and the reliance of the sidechannel jointly shape interpretability, revealing inherent trade-offs across different CSM architectures. Empirical results show that state-of-the-art CSMs, when trained solely for accuracy, exhibit low representation interpretability, and that SIS regularization substantially improves their interpretability, intervenability, and the quality of learned interpretable task predictors. Our work provides both theoretical and practical tools for developing CSMs that balance accuracy and interpretability in a principled manner.

Related papers

• Causal Neural Probabilistic Circuits [13.696507778417326]
  Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting the class label from the concept predictions.<n>We propose the Causal Neural Probabilistic Circuit (CNPC), which combines a neural attribute predictor with a causal probabilistic circuit compiled from a causal graph.<n>CNPC achieves higher task accuracy across different numbers of intervened attributes.
  arXiv  Detail & Related papers  (2026-03-02T02:15:24Z)
• Concepts' Information Bottleneck Models [9.435622803973898]
  Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer.<n>We introduce an explicit Information Bottleneck regularizer on the concept layer that penalizes $I(X;C)$ while preserving task-relevant information in $I(C;Y)$, encouraging minimal-sufficient concept representations.
  arXiv  Detail & Related papers  (2026-02-16T10:33:20Z)
• Efficient Thought Space Exploration through Strategic Intervention [54.35208611253168]
  We propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components.<n>The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), which dynamically identifies intervention points.<n> Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs.
  arXiv  Detail & Related papers  (2025-11-13T07:26:01Z)
• There Was Never a Bottleneck in Concept Bottleneck Models [27.888718857850822]
  Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue.<n>We argue that CBMs do not impose a true bottleneck: the fact that a component can predict a concept does not guarantee that it encodes only information about that concept.<n>We propose Minimal Concept Bottleneck Models (MCBMs), which incorporate an Information Bottleneck (IB) objective to constrain each representation component to retain only the information relevant to its corresponding concept.
  arXiv  Detail & Related papers  (2025-06-05T10:50:42Z)
• Adaptive Test-Time Intervention for Concept Bottleneck Models [6.31833744906105]
  Concept bottleneck models (CBM) aim to improve model interpretability by predicting human level "concepts"<n>We propose to use Fast Interpretable Greedy Sum-Trees (FIGS) to obtain Binary Distillation (BD)<n>FIGS-BD distills a binary-augmented concept-to-target portion of the CBM into an interpretable tree-based model.
  arXiv  Detail & Related papers  (2025-03-09T19:03:48Z)
• Topology-Aware Conformal Prediction for Stream Networks [54.505880918607296]
  We propose Spatio-Temporal Adaptive Conformal Inference (textttCISTA), a novel framework that integrates network topology and temporal dynamics into the conformal prediction framework.<n>Our results show that textttCISTA effectively balances prediction efficiency and coverage, outperforming existing conformal prediction methods for stream networks.
  arXiv  Detail & Related papers  (2025-03-06T21:21:15Z)
• Interpretable Concept-Based Memory Reasoning [12.562474638728194]
  Concept-based Memory Reasoner (CMR) is a novel CBM designed to provide a human-understandable and provably-verifiable task prediction process. CMR achieves better accuracy-interpretability trade-offs to state-of-the-art CBMs, discovers logic rules consistent with ground truths, allows for rule interventions, and allows pre-deployment verification.
  arXiv  Detail & Related papers  (2024-07-22T10:32:48Z)
• Linearly-Interpretable Concept Embedding Models for Text Analysis [9.340843984411137]
  We propose a novel Linearly Interpretable Concept Embedding Model (LICEM)<n>LICEMs classification accuracy is better than existing interpretable models and matches black-box ones.<n>We show that the explanations provided by our models are more interveneable and causally consistent with respect to existing solutions.
  arXiv  Detail & Related papers  (2024-06-20T14:04:53Z)
• 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)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• 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)
• An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction [84.49035467829819]
  We show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective. Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale.
  arXiv  Detail & Related papers  (2020-05-01T23:26:41Z)

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.