Fixed Point Explainability
This paper introduces a formal notion of fixed point explanations, inspired by the "why regress" principle, to assess, through recursive applications, the stability of the interplay between a model and its explainer. Fixed point explanations satisfy properties like minimality, stability, and faithfulness, revealing hidden model behaviours and explanatory weaknesses. We define convergence conditions for several classes of explainers, from feature-based to mechanistic tools like Sparse AutoEncoders, and we report quantitative and qualitative results.
Code (1)
Similar Papers 제목 키워드 기반
Surrogate Model-Based Explainability Methods for Point Cloud NNs
In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors. Therefore, point cloud neural networks have become a pop…
Autonomous DrivingPoint Cloud ClassificationVisualizing Global Explanations of Point Cloud DNNs
In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors. Therefore, point cloud neural networks have become a pop…
Autonomous DrivingPoint Cloud ClassificationExplainability-Aware One Point Attack for Point Cloud Neural Networks
With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of poin…
3D Object RecognitionAdversarial RobustnessObject RecognitionIntegration Of Evolutionary Automated Machine Learning With Structural Sensitivity Analysis For Composite Pipelines
Automated machine learning (AutoML) systems propose an end-to-end solution to a given machine learning problem, creating either fixed or flexible pipelines. Fixed pipelines are task independent constructs: their general …
AutoMLSensitivityExplainability matters: The effect of liability rules on the healthcare sector
Explainability, the capability of an artificial intelligence system (AIS) to explain its outcomes in a manner that is comprehensible to human beings at an acceptable level, has been deemed essential for critical sectors,…