Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models

• URL: http://arxiv.org/abs/2605.18202v1
• Date: Mon, 18 May 2026 10:43:02 GMT
• Title: Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
• Abstract summary: Neuro-Symbolic Concept-based Models (NeSy-CBMs) integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applications.<n>They work by first extracting high-level concepts from the input and then inferring a task label from these compatibly with given logical constraints.<n>We address this issue by integrating ideas from Conformal Prediction (CP), a framework providing rigorous, distribution-free coverage guarantees.<n>We then introduce COCOCO, a post-hoc framework that conformalizes concepts and labels jointly and reconciles them via a single deduction-abduction revision step.
• Score: 21.46859463155991
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applications. They work by first extracting high-level concepts from the input and then inferring a task label from these compatibly with given logical constraints. Yet, their label and concept predictions can be overconfident, making it difficult for stakeholders to gauge when the model's decisions can be trusted. We address this issue by integrating ideas from Conformal Prediction (CP), a framework providing rigorous, distribution-free coverage guarantees. We formalize three desiderata -- consistency, coverage, and conciseness -- that any conformal method for NeSy-CBMs should satisfy, and show that existing approaches fall short of at least one. We then introduce COCOCO, a post-hoc framework that conformalizes concepts and labels jointly and reconciles them via a single deduction-abduction revision step. COCOCO satisfies all three desiderata, retains distribution-free coverage, is robust to imperfect knowledge and supports user-specified size budgets. Our experiments on 8 data sets highlight how COCOCO compares favorably against competitors and natural baselines in terms of performance and set size.

Related papers

• Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints [80.85967228615388]
  We propose a principled constrained optimization framework that formulates unlearning as minimizing the deviation from a pretrained model.<n>We show that our KL-constrained approach achieves superior retention-based baselines for concept and data unlearning, and that our likelihood-based approach matches unlearning effectiveness.
  arXiv  Detail & Related papers  (2026-05-29T04:25:45Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering [75.50670592447219]
  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes.<n>This survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives.
  arXiv  Detail & Related papers  (2026-03-21T14:15:34Z)
• Rethinking Concept Bottleneck Models: From Pitfalls to Solutions [53.84388497227224]
  Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts.<n>CBM-Suite is a methodological framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-05T19:37:49Z)
• 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)
• Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation [57.427604620940734]
  We present textscConceptBank, a framework to restore alignment between visual evidence and prompts on the fly.<n>Our approach anchors target-domain evidence via class-wise visual prototypes, (textitii) mines representative supports to suppress outliers under data drift, and (textitiii) fuses candidate concepts to rectify concept drift.
  arXiv  Detail & Related papers  (2026-02-06T02:59:11Z)
• 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)
• Partially Shared Concept Bottleneck Models [15.871749983667229]
  Concept Bottleneck Models (CBMs) enhance interpretability by introducing a layer of human-understandable concepts between inputs and predictions.<n>Recent methods automate concept generation using Large Language Models (LLMs) and Vision-Language Models (VLMs)<n>We introduce PS-CBM, a Partially Shared CBM framework that addresses these limitations through three core components.
  arXiv  Detail & Related papers  (2025-11-27T07:15:15Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization [8.368983263620889]
  Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of AI systems by constraining their decisions on a set of human-understandable concepts.<n>CBMs typically assume that datasets contain accurate concept labels, which can significantly degrade performance.<n>We introduce the Concept Preference Optimization (CPO) objective, which effectively mitigates the negative impact of concept mislabeling on CBM performance.
  arXiv  Detail & Related papers  (2025-04-25T02:43:10Z)
• Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens [16.834053030732548]
  Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions.<n>We study this problem by establishing a novel connection between Concept-based Models and reasoning shortcuts (RSs)<n>Our empirical results highlight the impact of RSs and show that existing methods, even combined with multiple natural mitigation strategies, often fail to meet these conditions in practice.
  arXiv  Detail & Related papers  (2025-02-16T19:45:09Z)
• BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts [21.743306538494043]
  Reasoning Shortcuts can affect Neuro-Symbolic (NeSy) predictors. They learn concepts consistent with symbolic knowledge by exploiting unintended semantics. We propose to ensure NeSy models are aware of the semantic ambiguity of the concepts they learn.
  arXiv  Detail & Related papers  (2024-02-19T15:54:36Z)

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.