Personalized Interpretable

Personalized interpretable machine learning aims to create models that not only accurately predict individual outcomes but also provide transparent explanations for those predictions, addressing concerns about "black box" models. Current research focuses on developing federated learning frameworks that personalize models while preserving data privacy, often employing hierarchical Bayesian approaches or novel optimization algorithms like random block coordinate descent. This work is significant because it enhances trust and understanding in predictive models, particularly in sensitive applications like healthcare, by providing individualized insights and improving fairness through techniques that address data imbalances.

Papers

February 19, 2024

Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning
Kaan Ozkara, Bruce Huang, Ruida Zhou, Suhas Diggavi
Diffusion Model Data Heterogeneity Personalized Federated Learning Hierarchical Bayesian Personalized Interpretable

October 22, 2023

PPFL: A Personalized Federated Learning Framework for Heterogeneous Population
Hao Di, Yi Yang, Haishan Ye, Xiangyu Chang
Personalized Federated Learning Personalization Method Heterogeneous Population Personalized Interpretable

February 15, 2023

FedABC: Targeting Fair Competition in Personalized Federated Learning
Dui Wang, Li Shen, Yong Luo, Han Hu, Kehua Su, Yonggang Wen, Dacheng Tao
Class Imbalance Personalized Federated Learning Federated Averaging Binary Classification Loss Personalized Interpretable

February 6, 2023

Personalized Interpretable Classification
Zengyou He, Yifan Tang, Lianyu Hu, Mudi Jiang, Yan Liu
Interpretable Classifier Personalized Interpretable

Personalized Interpretable

Papers

Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning

PPFL: A Personalized Federated Learning Framework for Heterogeneous Population

FedABC: Targeting Fair Competition in Personalized Federated Learning

Personalized Interpretable Classification