# Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)

Source: [Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)](<https://www.sota2.com/research/paper/6997ea6809c33900fcd764a6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-21T05:00:04.173Z

Authors: Xiangyu Zhou, Chenhan Xiao, Yang Weng

Published: 2026-02-19T06:06:12.000Z

## Abstract

Shapley value-based methods have become foundational in explainable artificial intelligence (XAI), offering theoretically grounded feature attributions through cooperative game theory. However, in practice, particularly in vision tasks, the assumption of feature independence breaks down, as features (i.e., pixels) often exhibit strong spatial and semantic dependencies. To address this, modern SHAP implementations now include the Owen value, a hierarchical generalization of the Shapley value that supports group attributions. While the Owen value preserves the foundations of Shapley values, its effectiveness critically depends on how feature groups are defined. We show that commonly used segmentations (e.g., axis-aligned or SLIC) violate key consistency properties, and propose a new segmentation approach that satisfies the $T$-property to ensure semantic alignment across hierarchy levels. This hierarchy enables computational pruning while improving attribution accuracy and interpretability. Experiments on image and tabular datasets demonstrate that O-Shap outperforms baseline SHAP variants in attribution precision, semantic coherence, and runtime efficiency, especially when structure matters.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [XAI Evaluation on ImageNet-S50](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s50.md>): XAI Evaluation; ImageNet-S50; EBPG: 0.5692.

- [Feature Attribution on Image data 224 x 224](<https://www.sota2.com/research/sota/feature-attribution-on-image-data-224-x-224.md>): Feature Attribution; Image data 224 x 224; Avg Execution Time (s): 2.36.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.17107>)

[PDF](<https://arxiv.org/pdf/2602.17107.pdf>)