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 19, 2023

Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing
Andy Li, Milan Markovic, Peter Edwards, Georgios Leontidis
Federated Learning Data Heterogeneity Heterogeneous Data Model Pruning Data Sharing Plant Monitoring Yield Prediction

April 9, 2023

Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning
Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi, Kaushik Roy
Knowledge Distillation Data Set Decentralized Learning Heterogeneous Data Training Data Distribution

April 4, 2023

Learning from data with structured missingness
Robin Mitra, Sarah F. McGough, Tapabrata Chakraborti, Chris Holmes, Ryan Copping, Niels Hagenbuch, Stefanie Biedermann, Jack Noonan, Brieuc Lehmann, Aditi Shenvi, Xuan Vinh Doan, David Leslie, Ginestra Bianconi, Ruben Sanchez-Garcia, Alisha Davies, Maxine Mackintosh, Eleni-Rosalina Andrinopoulou, Anahid Basiri, Chris Harbron, Ben D. MacArthur
LeArning Abstract Raw Data Heterogeneous Data Classification Task Missing Data Missingness Pattern

March 4, 2023

Federated Virtual Learning on Heterogeneous Data with Local-global Distillation
Chun-Yin Huang, Ruinan Jin, Can Zhao, Daguang Xu, Xiaoxiao Li
Dataset Distillation Heterogeneous Data Global Distillation

March 1, 2023

A Unified Momentum-based Paradigm of Decentralized SGD for Non-Convex Models and Heterogeneous Data
Haizhou Du, Chengdong Ni
Heterogeneous Data Decentralized Machine Learning Momentum Based Non Convex Objective Decentralized SGD Convex Model

February 20, 2023

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI
Juexiao Zhou, Longxi Zhou, Di Wang, Xiaopeng Xu, Haoyang Li, Yuetan Chu, Wenkai Han, Xin Gao
Homomorphic Encryption Heterogeneous Data Personalized Subject Heterogeneous Medical Image

February 16, 2023

Distributed Learning in Heterogeneous Environment: federated learning with adaptive aggregation and computation reduction
Jingxin Li, Toktam Mahmoodi, Hak-Keung Lam
LeArning Abstract Heterogeneous Data Global Mixing Heterogeneous Environment Training Instability Complexity Reduction Adaptive Aggregation Asynchronous Update

February 14, 2023

February 13, 2023

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting
Yuchen Liu, Chen Chen, Lingjuan Lyu, Fangzhao Wu, Sai Wu, Gang Chen
Heterogeneous Data Byzantine Robust Byzantine Attack Robust Aggregation Rule

February 11, 2023

Fairness-aware Multi-view Clustering
Lecheng Zheng, Yada Zhu, Jingrui He
Data Heterogeneity Group Fairness Heterogeneous Data Multi View Clustering Fair Clustering

February 8, 2023

Towards Model-Agnostic Federated Learning over Networks
A. Jung, S. Abdurakhmanova, O. Kuznetsova, Y. SarcheshmehPour
Network Programming Empirical Risk Minimization Heterogeneous Data Local Model Scikit Learn Agnostic Federated Learning

February 3, 2023

Convergence Analysis of Sequential Split Learning on Heterogeneous Data
Yipeng Li, Xinchen Lyu
Convergence Analysis Heterogeneous Data Convergence Guarantee Split Learning Federated Averaging

January 21, 2023

The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation
Huancheng Chen, Johnny, Wang, Haris Vikalo
Knowledge Distillation World Event Heterogeneous Data Personalized Model High Accuracy

December 17, 2022

Toward Data Heterogeneity of Federated Learning
Yuchuan Huang, Chen Hu
Machine Learning Data Heterogeneity Heterogeneous Data

December 5, 2022

On the effectiveness of partial variance reduction in federated learning with heterogeneous data
Bo Li, Mikkel N. Schmidt, Tommy S. Alstrøm, Sebastian U. Stich
LeArning Abstract Data Heterogeneity Heterogeneous Data Variance Reduction FedAvg Algorithm Gradient Update Client Drift

November 26, 2022

Deep neuroevolution for limited, heterogeneous data: proof-of-concept application to Neuroblastoma brain metastasis using a small virtual pooled image collection
Subhanik Purkayastha, Hrithwik Shalu, David Gutman, Shakeel Modak, Ellen Basu, Brian Kushner, Kim Kramer, Sofia Haque, Joseph Stember
Artificial Intelligence Large Scale Stronger Generalizability Heterogeneous Data Proof of Concept

November 17, 2022

FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
Tailin Zhou, Jun Zhang, Danny H. K. Tsang
Simple Classifier Heterogeneous Data Feature Space Feature Alignment Visual Information Anchor Data Divergence

November 13, 2022

Drug-target affinity prediction method based on consistent expression of heterogeneous data
Boyuan Liu
Strong Consistency Drug Discovery Heterogeneous Data Drug Target Drug Target Pair Drug Target Affinity Prediction Drug Node

October 30, 2022

Evaluation and comparison of federated learning algorithms for Human Activity Recognition on smartphones
Sannara Ek, François Portet, Philippe Lalanda, German Vega
Machine Learning Practical Algorithm Global Evaluation Consistent Comparison Activity Recognition Heterogeneous Data Smartphone Device Pervasive Computing

Heterogeneous Data

Papers

Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing

Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning

Learning from data with structured missingness

Federated Virtual Learning on Heterogeneous Data with Local-global Distillation

A Unified Momentum-based Paradigm of Decentralized SGD for Non-Convex Models and Heterogeneous Data

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI

Distributed Learning in Heterogeneous Environment: federated learning with adaptive aggregation and computation reduction

EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data

Heterogeneous Anomaly Detection for Software Systems via Semi-supervised Cross-modal Attention

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

Fairness-aware Multi-view Clustering

Towards Model-Agnostic Federated Learning over Networks

Convergence Analysis of Sequential Split Learning on Heterogeneous Data

The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation

Toward Data Heterogeneity of Federated Learning

On the effectiveness of partial variance reduction in federated learning with heterogeneous data

Deep neuroevolution for limited, heterogeneous data: proof-of-concept application to Neuroblastoma brain metastasis using a small virtual pooled image collection

FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data

Drug-target affinity prediction method based on consistent expression of heterogeneous data

Evaluation and comparison of federated learning algorithms for Human Activity Recognition on smartphones