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

May 31, 2024

Non-Federated Multi-Task Split Learning for Heterogeneous Sources
Yilin Zheng, Atilla Eryilmaz
Data Heterogeneity Heterogeneous Data Split Learning Heterogeneous Computing Heterogeneous Source Federated Split Learning

May 27, 2024

Dual-Delayed Asynchronous SGD for Arbitrarily Heterogeneous Data
Xiaolu Wang, Yuchang Sun, Hoi-To Wai, Jun Zhang
Heterogeneous Data Asynchronous Training Asynchronous Stochastic Gradient Descent

May 22, 2024

SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data
Sakshi Choudhary, Sai Aparna Aketi, Kaushik Roy
Deep Learning Algorithm Heterogeneous Data Sharpness Aware Minimization Communication Compression Decentralized Training Decentralized Deep Learning Saddle to Saddle Dynamic

May 21, 2024

May 2, 2024

Sharp Bounds for Sequential Federated Learning on Heterogeneous Data
Yipeng Li, Xinchen Lyu
Federated Learning Heterogeneous Data Convergence Guarantee Convex Function Non Convex Objective Convex Objective Sharp Bound

April 25, 2024

GuideWalk: A Novel Graph-Based Word Embedding for Enhanced Text Classification
Sarmad N. Mohammed, Semra Gündüç
Machine Learning Text Classification Heterogeneous Data Text Data Data Fusion Seated Walk Enhanced Learning Multi Label Document Classification

March 25, 2024

FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data
Yuxin Zhang, Haoyu Chen, Zheng Lin, Zhe Chen, Jin Zhao
Heterogeneous Data Layer Wise Clustered Federated Learning

March 21, 2024

Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server
Fei Li, Chu Kiong Loo, Wei Shiung Liew, Xiaofeng Liu
Multi Task Learning Heterogeneous Data Efficient Approach FedProx Algorithm Feature Name Simultaneous Improvement

March 5, 2024

Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data
Sai Aparna Aketi, Sakshi Choudhary, Kaushik Roy
Decentralized Learning Heterogeneous Data Data Distribution Unobserved Heterogeneity Variable Rate

March 3, 2024

Quantized Hierarchical Federated Learning: A Robust Approach to Statistical Heterogeneity
Seyed Mohammad Azimi-Abarghouyi, Viktoria Fodor
Heterogeneous Data Model Aggregation Robust Framework Hierarchical Federated Learning Statistical Heterogeneity Aggregated Gradient

February 26, 2024

Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models
Jinqian Chen, Jihua Zhu, Qinghai Zheng, Zhongyu Li, Zhiqiang Tian
Heterogeneous Data Human Head Federated Setting Ensemble Diversity Reliable Prediction Projection Head

February 23, 2024

Convergence Analysis of Split Federated Learning on Heterogeneous Data
Pengchao Han, Chao Huang, Geng Tian, Ming Tang, Xin Liu
Model Training Convergence Analysis Heterogeneous Data Non Convex Objective Split Federated Learning Convex Objective

February 20, 2024

February 16, 2024

TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data
Richeng Jin, Yujie Gu, Kai Yue, Xiaofan He, Zhaoyang Zhang, Huaiyu Dai
Differential Privacy Heterogeneous Data Communication Efficiency Byzantine Robust Privacy Amplification Ternary Random Variable

February 9, 2024

BarlowTwins-CXR : Enhancing Chest X-Ray abnormality localization in heterogeneous data with cross-domain self-supervised learning
Haoyue Sheng, Linrui Ma, Jean-Francois Samson, Dianbo Liu
Heterogeneous Data VinDr CXR Domain Self Abnormality Localization

January 1, 2024

A review on different techniques used to combat the non-IID and heterogeneous nature of data in FL
Venkataraman Natarajan Iyer
Federated Learning Raw Data Narrative Review Model Training Heterogeneous Data Model Convergence

December 11, 2023

Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
Yuqin Yang, Saber Salehkaleybar, Negar Kiyavash
LeArning Abstract Causal Model Structural Causal Model Heterogeneous Data Latent Confounders Global Endogenous Variate Unknown Intervention Causal Overhypotheses

December 7, 2023

Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data
Feifei Wang, Huiyun Tang, Yang Li
Data Heterogeneity Heterogeneous Data Machine Learning Framework Tucker Decomposition

Heterogeneous Data

Papers

Non-Federated Multi-Task Split Learning for Heterogeneous Sources

Dual-Delayed Asynchronous SGD for Arbitrarily Heterogeneous Data

SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data

Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous Data

Stochastic Inference of Plate Bending from Heterogeneous Data: Physics-informed Gaussian Processes via Kirchhoff-Love Theory

Sharp Bounds for Sequential Federated Learning on Heterogeneous Data

GuideWalk: A Novel Graph-Based Word Embedding for Enhanced Text Classification

FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data

Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server

Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data

Quantized Hierarchical Federated Learning: A Robust Approach to Statistical Heterogeneity

Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models

Convergence Analysis of Split Federated Learning on Heterogeneous Data

Federated Causal Discovery from Heterogeneous Data

CCFC++: Enhancing Federated Clustering through Feature Decorrelation

TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data

BarlowTwins-CXR : Enhancing Chest X-Ray abnormality localization in heterogeneous data with cross-domain self-supervised learning

A review on different techniques used to combat the non-IID and heterogeneous nature of data in FL

Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data

Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data