Selected work

Representative Papers

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

Feb 04, 2026

This work addresses the limitations of existing hierarchical Shapley methods, which overlook the multi-scale structure inherent in images, resulting in slow convergence, weak semantic alignment, and data-agnostic hierarchical partitions. To overcome these issues, the paper introduces, for the first time, a data-driven binary partition tree (BPT) into the hierarchical Shapley framework, thereby constructing a multi-scale hierarchy that aligns with the intrinsic morphological structure of images. This approach enables efficient and semantically coherent pixel-level feature attribution. The proposed method significantly outperforms current techniques in both computational efficiency and structural alignment, and achieves higher user preference in a study involving 20 participants.

0 citationsRead paper

Enhancing interpretability of rule-based classifiers through feature graphs

Jun 16, 2025

In high-stakes domains (e.g., healthcare), interpreting feature importance in complex rule-based models—and comparing importance across disparate rule sets—remains challenging. To address this, we propose the first graph-structured framework for feature interpretability. Methodologically: (1) we construct a model-agnostic graph representation of features, capturing relational and hierarchical semantics; (2) we design a unified attribution algorithm for quantifying feature importance grounded in causal contribution; and (3) we define a distance metric between rule sets based on divergence of their feature contribution distributions. The framework supports diverse models—including decision trees, LLMs, association rules, and neuro-symbolic systems—and integrates a robustness evaluation module. Empirically, it identifies biologically plausible biomarkers and high-order feature interactions on clinical datasets; achieves state-of-the-art performance across 15 benchmarks with significantly improved robustness; and its open-source implementation has seen widespread adoption in both research and clinical applications.

0 citationsRead paper

Recent publications

Latest Papers

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

Feb 04, 2026

This work addresses the limitations of existing hierarchical Shapley methods, which overlook the multi-scale structure inherent in images, resulting in slow convergence, weak semantic alignment, and data-agnostic hierarchical partitions. To overcome these issues, the paper introduces, for the first time, a data-driven binary partition tree (BPT) into the hierarchical Shapley framework, thereby constructing a multi-scale hierarchy that aligns with the intrinsic morphological structure of images. This approach enables efficient and semantically coherent pixel-level feature attribution. The proposed method significantly outperforms current techniques in both computational efficiency and structural alignment, and achieves higher user preference in a study involving 20 participants.

0 citationsRead paper

Enhancing interpretability of rule-based classifiers through feature graphs

Jun 16, 2025

In high-stakes domains (e.g., healthcare), interpreting feature importance in complex rule-based models—and comparing importance across disparate rule sets—remains challenging. To address this, we propose the first graph-structured framework for feature interpretability. Methodologically: (1) we construct a model-agnostic graph representation of features, capturing relational and hierarchical semantics; (2) we design a unified attribution algorithm for quantifying feature importance grounded in causal contribution; and (3) we define a distance metric between rule sets based on divergence of their feature contribution distributions. The framework supports diverse models—including decision trees, LLMs, association rules, and neuro-symbolic systems—and integrates a robustness evaluation module. Empirically, it identifies biologically plausible biomarkers and high-order feature interactions on clinical datasets; achieves state-of-the-art performance across 15 benchmarks with significantly improved robustness; and its open-source implementation has seen widespread adoption in both research and clinical applications.

0 citationsRead paper