Heterogeneous Data

Heterogeneous data, encompassing datasets with varying distributions, formats, and qualities across sources, presents a significant challenge in machine learning. Current research focuses on developing robust algorithms and model architectures, such as federated learning with adaptive aggregation and personalized models, to effectively handle this heterogeneity in diverse applications like medical imaging and industrial settings. These efforts aim to improve model accuracy, fairness, and robustness while addressing privacy concerns inherent in decentralized data collection. The successful management of heterogeneous data is crucial for advancing machine learning's applicability to real-world problems where data is inherently diverse and distributed.

Papers

April 7, 2022

FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity
Yonghai Gong, Yichuan Li, Nikolaos M. Freris
Adaptive Importance Primal Dual Heterogeneous Data Non Convex Objective Robust Federated Learning System Heterogeneity

March 4, 2022

Continual Horizontal Federated Learning for Heterogeneous Data
Junki Mori, Isamu Teranishi, Ryo Furukawa
Machine Learning Continual Learning Heterogeneous Data Local Learning Heterogeneous Input Horizontal Federated Learning

January 31, 2022

Reinforcement Learning with Heterogeneous Data: Estimation and Inference
Elynn Y. Chen, Rui Song, Michael I. Jordan
Reinforcement Learning Scientific Inference Estimation Task Heterogeneous Data Policy Iteration

January 24, 2022

Scaling Up Knowledge Graph Creation to Large and Heterogeneous Data Sources
Enrique Iglesias, Samaneh Jozashoori, Maria-Esther Vidal
Heterogeneous Data RDF Schema RDF Triple Heterogeneous Data Source RDF Knowledge Graph

January 9, 2022

Robust classification with flexible discriminant analysis in heterogeneous data
Pierre Houdouin, Frédéric Pascal, Matthieu Jonckheere, Andrew Wang
Heterogeneous Data Maximum Likelihood Cyclic Symmetry Discriminant Analysis Non Gaussian Robust Classification Robust Principal Component Analysis Quadratic Discriminant Analysis

December 25, 2021

Towards Federated Learning on Time-Evolving Heterogeneous Data
Yongxin Guo, Tao Lin, Xiaoying Tang
Heterogeneous Data Federated Continual Learning Heterogeneous Tabular Data

December 17, 2021

December 10, 2021

PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records
Tianyi Zhang, Shirui Zhang, Ziwei Chen, Dianbo Liu
Financial Application Federated Learning Heterogeneous Data Patient Data Heterogeneous Clinical Federated Machine Learning Heterogeneous Task Federated Meta Learning

December 1, 2021

Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
Ha Min Son, Moon Hyun Kim, Tai-Myoung Chung
Neural Network Consistent Comparison Heterogeneous Data Deep Learning Task Kernel Alignment Layer Regularization Centered Kernel Alignment

November 19, 2021

Client Selection in Federated Learning based on Gradients Importance
Ouiame Marnissi, Hajar El Hammouti, El Houcine Bergou
Heterogeneous Data Gradient Norm Client Selection Communication Efficiency Gradient Information Device Selection

November 17, 2021

Differentially Private Federated Learning on Heterogeneous Data
Maxence Noble, Aurélien Bellet, Aymeric Dieuleveut
Differential Privacy Heterogeneous Data Private Federated Learning Privacy Utility Trade

November 12, 2021

Detecting Quality Problems in Data Models by Clustering Heterogeneous Data Values
Viola Wenz, Arno Kesper, Gabriele Taentzer
Data Heterogeneity Heterogeneous Data Cultural Heritage Data Model