Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks

• URL: http://arxiv.org/abs/2506.05533v1
• Date: Thu, 05 Jun 2025 19:30:20 GMT
• Title: Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks
• Authors: Tomasz Michalski, Adam Wróbel, Andrea Bontempelli, Jakub Luśtyk, Mikolaj Kniejski, Stefano Teso, Andrea Passerini, Bartosz Zieliński, Dawid Rymarczyk,
• Abstract summary: Concept-based interpretable neural networks have gained significant attention due to their intuitive and easy-to-understand explanations.<n>A major limitation is that these explanations may not always be comprehensible to users due to concept inconsistency.<n>This inconsistency breaks the alignment between model reasoning and human understanding.<n>We introduce YoursProtoP, a novel interactive strategy that enables the personalization of prototypical parts.
• Score: 16.958657905772846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Concept-based interpretable neural networks have gained significant attention due to their intuitive and easy-to-understand explanations based on case-based reasoning, such as "this bird looks like those sparrows". However, a major limitation is that these explanations may not always be comprehensible to users due to concept inconsistency, where multiple visual features are inappropriately mixed (e.g., a bird's head and wings treated as a single concept). This inconsistency breaks the alignment between model reasoning and human understanding. Furthermore, users have specific preferences for how concepts should look, yet current approaches provide no mechanism for incorporating their feedback. To address these issues, we introduce YoursProtoP, a novel interactive strategy that enables the personalization of prototypical parts - the visual concepts used by the model - according to user needs. By incorporating user supervision, YoursProtoP adapts and splits concepts used for both prediction and explanation to better match the user's preferences and understanding. Through experiments on both the synthetic FunnyBirds dataset and a real-world scenario using the CUB, CARS, and PETS datasets in a comprehensive user study, we demonstrate the effectiveness of YoursProtoP in achieving concept consistency without compromising the accuracy of the model.

Related papers

• Interpretable Reward Modeling with Active Concept Bottlenecks [54.00085739303773]
  We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning.<n>Unlike standard RLHF methods that rely on opaque reward functions, CB-RM decomposes reward prediction into human-interpretable concepts.<n>We formalize an active learning strategy that dynamically acquires the most informative concept labels.
  arXiv  Detail & Related papers  (2025-07-07T06:26:04Z)
• 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)
• Neural Concept Binder [22.074896812195437]
  We introduce the Neural Concept Binder (NCB), a framework for deriving both discrete and continuous concept representations. The structured nature of NCB's concept representations allows for intuitive inspection and the straightforward integration of external knowledge. We validate the effectiveness of NCB through evaluations on our newly introduced CLEVR-Sudoku dataset.
  arXiv  Detail & Related papers  (2024-06-14T11:52:09Z)
• Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models [57.86303579812877]
  Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Existing approaches often require numerous human interventions per image to achieve strong performances. We introduce a trainable concept realignment intervention module, which leverages concept relations to realign concept assignments post-intervention.
  arXiv  Detail & Related papers  (2024-05-02T17:59:01Z)
• 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)
• Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models [53.337728969143086]
  Recommendation systems harness user-item interactions like clicks and reviews to learn their representations. Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents. We introduce a chain-based prompting approach to uncover semantic aspect-aware interactions.
  arXiv  Detail & Related papers  (2023-12-26T15:44:09Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Selective Concept Models: Permitting Stakeholder Customisation at Test-Time [32.138390859351425]
  We propose Selective COncept Models (SCOMs) which make predictions using only a subset of concepts. We show that SCOMs only require a fraction of the total concepts to achieve optimal accuracy on multiple real-world datasets. Using CUB-Sel, we show that humans have unique individual preferences for the choice of concepts they prefer to reason about.
  arXiv  Detail & Related papers  (2023-06-14T10:37:13Z)
• Translational Concept Embedding for Generalized Compositional Zero-shot Learning [73.60639796305415]
  Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework.
  arXiv  Detail & Related papers  (2021-12-20T21:27:51Z)
• Learning Interpretable Concept-Based Models with Human Feedback [36.65337734891338]
  We propose an approach for learning a set of transparent concept definitions in high-dimensional data that relies on users labeling concept features. Our method produces concepts that both align with users' intuitive sense of what a concept means, and facilitate prediction of the downstream label by a transparent machine learning model.
  arXiv  Detail & Related papers  (2020-12-04T23:41:05Z)
• Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations [24.327862278556445]
  We propose a Neuro-Symbolic scene representation, which allows one to revise the model on the semantic level. The results of our experiments on CLEVR-Hans demonstrate that our semantic explanations can identify confounders.
  arXiv  Detail & Related papers  (2020-11-25T16:23:26Z)

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.