5 papers
Correcting Variable Importance Scored by Random Forests
Guancheng Zhou, Haiping Xu, Jason Liu +1
Variable importance produced by Random Forests (RF) is used widely in statistical data analysis, and has played an important role in a variety of tasks such as assisting model inte…
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
Guancheng Zhou, Yisi Luo, Zhengfu He +5
Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top- activatio…
Tracing the Thought of a Grandmaster-level Chess-Playing Transformer
Rui Lin, Zhenyu Jin, Guancheng Zhou +7
While modern transformer neural networks achieve grandmaster-level performance in chess and other reasoning tasks, their internal computation process remains largely opaque. Focusi…
Critical Challenges in Content Moderation for People Who Use Drugs (PWUD): Insights into Online Harm Reduction Practices from Moderators
Kaixuan Wang, Loraine Clarke, Carl-Cyril J Dreue +2
Online communities serve as essential support channels for People Who Use Drugs (PWUD), providing access to peer support and harm reduction information. The moderation of these com…
A Computational Approach to Improving Fairness in K-means Clustering
Guancheng Zhou, Haiping Xu, Hongkang Xu +2
The popular K-means clustering algorithm potentially suffers from a major weakness for further analysis or interpretation. Some cluster may have disproportionately more (or fewer)…