Multiscale Feature Attribution for Outliers

2023-10-30 · Jeff Shen, Peter Melchior

Machine learning techniques can automatically identify outliers in massive datasets, much faster and more reproducible than human inspection ever could. But finding such outliers immediately leads to the question: which features render this input anomalous? We propose a new feature attribution method, Inverse Multiscale Occlusion, that is specifically designed for outliers, for which we have little knowledge of the type of features we want to identify and expect that the model performance is questionable because anomalous test data likely exceed the limits of the training data. We demonstrate our method on outliers detected in galaxy spectra from the Dark Energy Survey Instrument and find its results to be much more interpretable than alternative attribution approaches.

📄 PDF Abstract BibTeX arXiv:2310.20012

Code (0)

등록된 구현이 없습니다.

ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees

2026-02-04 · Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda arxiv

Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley…

Attribution via Distributional Paths for Information Revelation

2026-06-02 · Kieran A. Murphy, Shameen Shrestha arxiv

Feature attribution methods explain predictions by assigning importance scores to input features. Path-based methods such as Integrated Gradients are especially appealing because they satisfy \textit{completeness}: attri…

Score-based Integrated Gradient for Root Cause Explanations of Outliers

2026-01-29 · Phuoc Nguyen, Truyen Tran, Sunil Gupta, Svetha Venkatesh arxiv

Identifying the root causes of outliers is a fundamental problem in causal inference and anomaly detection. Traditional approaches based on heuristics or counterfactual reasoning often struggle under uncertainty and high…

Computational Efficiency Anomaly Detection Causal Inference

Causal-discovery-based root-cause analysis and its application in time-series prediction error diagnosis

2024-11-11 · Hiroshi Yokoyama, Ryusei Shingaki, Kaneharu Nishino, Shohei Shimizu 외

Recent rapid advancements of machine learning have greatly enhanced the accuracy of prediction models, but most models remain "black boxes", making prediction error diagnosis challenging, especially with outliers. This l…

Causal Discovery Prediction Time Series Time Series Prediction

Nonparametric Data Attribution for Diffusion Models

2025-10-16 · Yutian Zhao, Chao Du, Xiaosen Zheng, Tianyu Pang 외 arxiv

Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, li…