← Search

Geyu Liang

2 accepted papers

2025

Enhancing Performance of Explainable AI Models with Constrained Concept Refinement

ICML 2025poster

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging *interpretable-by-design* methods, which aim to redesign ML algorithms for trustworthy interpretability but often sacrifice accuracy in the pr…

Cited by 2SourcePDFScholar
2023

Personalized Dictionary Learning for Heterogeneous Datasets

NeurIPS 2023poster

We introduce a relevant yet challenging problem named Personalized Dictionary Learning (PerDL), where the goal is to learn sparse linear representations from heterogeneous datasets that share some commonality. In PerDL, we model each dataset's shared and unique features as global and local dictionar…

Cited by 8SourcePDFScholar