arXiv AI

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

arXiv Machine Learning
Aug 27

ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing

ICON Decomposition is a new method for explaining deep neural networks by quantifying how much variance each concept explains in a network layer after accounting for all other concepts and the outcome. Unlike previous concept‑based methods that evaluate concepts in isolation, ICON can distinguish genuine model reliance from spurious correlations. Experiments on synthetic data, skin‑lesion, and brain‑imaging models show that ICON recovers concept importance more accurately, isolates truly relied‑upon concepts, and provides sparse explanations validated through retraining and out‑of‑distribution testing.

By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
arXiv AI
2d ago

ICON Decomposition: Auditing deep neural networks for shortcuts by decomposing layer-wise representations using concepts

The paper introduces ICON Decomposition, a method for auditing deep neural networks by decomposing layer-wise representations into independent concept contributions. Unlike existing techniques that rely on linear probes or concept activation vectors, ICON quantifies the variance share each concept explains while conditioning on all other concepts and the outcome, allowing comparison across layers and concept types. Experiments on simulated data, skin‑cancer, and neuroimaging models show that ICON more accurately recovers true concept importance and can distinguish learned shortcuts from correlated concepts, as validated by retraining and out‑of‑distribution tests.

By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
arXiv Machine Learning
Jun 9

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape

arXiv:2403. 06013v2 Announce Type: replace Abstract: This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated.

By Tiejin Chen, Wenwang Huang, Linsey Pang, Dongsheng Luo, Hua Wei
arXiv Machine Learning
Sep 7

SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis

The paper introduces SMILE, a self‑explainable multimodal information bottleneck framework for medical diagnosis. It jointly optimizes predictive accuracy and modality‑specific explainability by selecting the most informative elements within each data modality. Experiments on diverse medical datasets show strong diagnostic performance, including a 9.1‑percentage‑point accuracy gain on the iCTCF dataset, and provide transparent, modality‑aware explanations that enhance both explainability and generalization.

By Yuqing Yang, Alexander Schmatz, Zhaozhao Ma, Changkyu Choi, Robert Jenssen, Shujian Yu