Mixture of Concept Bottleneck Experts

• URL: http://arxiv.org/abs/2602.02886v1
• Date: Mon, 02 Feb 2026 22:44:42 GMT
• Title: Mixture of Concept Bottleneck Experts
• Authors: Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Mateo Espinosa Zarlenga, Pietro Barbiero, Johannes Schneider, Danilo Giordano,
• Abstract summary: Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts.<n>We propose a framework that generalizes existing CBMs along two dimensions: the number of experts and the functional form of each expert.
• Score: 18.412571821774158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically fix their task predictor to a single linear or Boolean expression, limiting both predictive accuracy and adaptability to diverse user needs. We propose Mixture of Concept Bottleneck Experts (M-CBEs), a framework that generalizes existing CBMs along two dimensions: the number of experts and the functional form of each expert, exposing an underexplored region of the design space. We investigate this region by instantiating two novel models: Linear M-CBE, which learns a finite set of linear expressions, and Symbolic M-CBE, which leverages symbolic regression to discover expert functions from data under user-specified operator vocabularies. Empirical evaluation demonstrates that varying the mixture size and functional form provides a robust framework for navigating the accuracy-interpretability trade-off, adapting to different user and task needs.

Related papers

• Controllable Concept Bottleneck Models [55.03639763625018]
  Controllable Concept Bottleneck Models (CCBMs)<n>CCBMs support three granularities of model editing: concept-label-level, concept-level, and data-level.<n>CCBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for retraining.
  arXiv  Detail & Related papers  (2026-01-01T19:30:06Z)
• A Geometric Unification of Concept Learning with Concept Cones [58.70836885177496]
  Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs) and Sparse Autoencoders (SAEs)<n>We show that both paradigms instantiate the same geometric structure.<n>CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs.
  arXiv  Detail & Related papers  (2025-12-08T09:51:46Z)
• Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder [59.89996751196727]
  Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models.<n>SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs.<n>Recent Mixture of Experts (MoE) approaches attempt to address this by SAEs into narrower expert networks with gated activation.<n>We propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling.
  arXiv  Detail & Related papers  (2025-11-07T22:19:34Z)
• Foundation Model for Skeleton-Based Human Action Understanding [56.89025287217221]
  This paper presents a Unified Skeleton-based Dense Representation Learning framework.<n>USDRL consists of a Transformer-based Dense Spatio-Temporal (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT)
  arXiv  Detail & Related papers  (2025-08-18T02:42:16Z)
• 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)
• Convergence Rates for Softmax Gating Mixture of Experts [78.3687645289918]
  Mixture of experts (MoE) has emerged as an effective framework to advance the efficiency and scalability of machine learning models.<n>Central to the success of MoE is an adaptive softmax gating mechanism which takes responsibility for determining the relevance of each expert to a given input and then dynamically assigning experts their respective weights.<n>We perform a convergence analysis of parameter estimation and expert estimation under the MoE equipped with the standard softmax gating or its variants, including a dense-to-sparse gating and a hierarchical softmax gating.
  arXiv  Detail & Related papers  (2025-03-05T06:11:24Z)
• Survival Concept-Based Learning Models [2.024925013349319]
  Two novel models are proposed to integrate concept-based learning with survival analysis.<n>SurvCBM is based on the architecture of the well-known concept bottleneck model.<n>SurvRCM uses concepts as regularization to enhance accuracy.
  arXiv  Detail & Related papers  (2025-02-09T16:41:04Z)
• Intrinsic User-Centric Interpretability through Global Mixture of Experts [31.738009841932374]
  InterpretCC is a family of intrinsically interpretable neural networks that optimize for ease of human understanding and explanation faithfulness.<n>We show that InterpretCC explanations are found to have higher actionability and usefulness over other intrinsically interpretable approaches.
  arXiv  Detail & Related papers  (2024-02-05T11:55:50Z)
• Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition [51.66383337087724]
  The Handwritten Mathematical Expression Recognition (HMER) task is a critical branch in the field of OCR. Recent studies have demonstrated that incorporating bidirectional context information significantly improves the performance of HMER models. We propose the Mirror-Flipped Symbol Layout Tree (MF-SLT) and Bidirectional Asynchronous Training (BAT) structure.
  arXiv  Detail & Related papers  (2023-12-31T09:24:21Z)
• Relational Concept Bottleneck Models [13.311396882130033]
  Concept Bottleneck Models (CBMs) are not designed to solve problems. R-CBMs are capable of both representing standard CBMs and relational GNNs. In particular, we show that R-CBMs support the generation of concept-based explanations.
  arXiv  Detail & Related papers  (2023-08-23T08:25:33Z)
• Interpretable Mixture of Experts [71.55701784196253]
  Interpretable Mixture of Experts (IME) is an inherently-interpretable modeling framework. IME is demonstrated to be more accurate than single interpretable models and perform comparably with existing state-of-the-art Deep Neural Networks (DNNs) in accuracy. IME's explanations are compared to commonly-used post-hoc explanations methods through a user study.
  arXiv  Detail & Related papers  (2022-06-05T06:40:15Z)
• Finding Experts in Transformer Models [2.105564340986074]
  We study the presence of expert units in pre-trained Transformer Models (TM), and how they impact a model's performance. We compile a dataset of 1641 concepts that allows diverse expert units in TM to be discovered. We show how to self-condition off-the-shelf pre-trained language models to generate text with a given concept by forcing the top experts to be active.
  arXiv  Detail & Related papers  (2020-05-15T17:07:02Z)

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.