ICON Decomposition: Auditing Deep Neural Networks with Multivariate Variance-based Concept-level Explanations

• URL: http://arxiv.org/abs/2608.26083v2
• Date: Mon, 31 Aug 2026 17:35:50 GMT
• Title: ICON Decomposition: Auditing Deep Neural Networks with Multivariate Variance-based Concept-level Explanations
• Abstract summary: Deep neural networks often exploit spurious associations, a failure known as shortcut learning.<n>Current concept-based explainability methods test one concept at a time, asking whether it is decodable from a layer.<n>We introduce ICON decomposition, which quantifies how much of a layer's variance each concept explains given all other concepts and the outcome.<n>On simulated data, ICON recovers concept importance more accurately than seven existing methods.
• Score: 15.846631139316678
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Auditing for shortcuts requires testing many candidate concepts, such as acquisition settings or demographics. Current concept-based explainability methods test one concept at a time, asking whether it is decodable from a layer. These methods flag concepts that are merely correlated with the outcome or with each other, and their scores are not comparable across layers or concept types. We introduce ICON decomposition, which quantifies how much of a layer's variance each concept explains given all other concepts and the outcome, and how much none of them explains, yielding layer-comparable, calibrated scores that suppress false positives. On simulated data, ICON recovers concept importance more accurately than seven existing methods. On skin-cancer models with inserted artifacts, it detects induced shortcuts where baselines report false positives. On two brain-imaging models, ICON's sparse explanations are validated by retraining and out-of-distribution tests.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• 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)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Concept-Guided Interpretability via Neural Chunking [64.6429903327095]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract recurring chunks on a neural population level.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• 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)
• Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
  Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
  arXiv  Detail & Related papers  (2024-07-19T17:50:11Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)
• Attributing Learned Concepts in Neural Networks to Training Data [5.930268338525991]
  We find evidence for convergence, where removing the 10,000 top attributing images for a concept and retraining the model does not change the location of the concept in the network. This suggests that the features that inform the development of a concept are spread in a more diffuse manner across its exemplars, implying robustness in concept formation.
  arXiv  Detail & Related papers  (2023-10-04T20:26:59Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Unit Testing for Concepts in Neural Networks [20.86261546611472]
  We propose unit tests for evaluating whether a system's behavior is consistent with Fodor's criteria. We find that models succeed on tests of groundedness, modularlity, and reusability of concepts, but that important questions about causality remain open.
  arXiv  Detail & Related papers  (2022-07-28T08:49:32Z)
• Probing Classifiers are Unreliable for Concept Removal and Detection [18.25734277357466]
  Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Recent work has proposed post-hoc and adversarial methods to remove such unwanted concepts from a model's representation. We show that these methods can be counter-productive, and in the worst case may end up destroying all task-relevant features.
  arXiv  Detail & Related papers  (2022-07-08T23:15:26Z)
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals [33.65478845353047]
  DISSECT is a novel approach to explaining deep learning model inferences. By training a generative model from a classifier's signal, DISSECT offers a way to discover a classifier's inherent "notion" of distinct concepts. We show that DISSECT produces CTs that disentangle several concepts and are coupled to its reasoning due to joint training.
  arXiv  Detail & Related papers  (2021-05-31T17:11:56Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)

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.