Heterogeneous Setting

Heterogeneous settings in machine learning address the challenges arising from diverse data distributions and resource limitations across distributed clients or devices. Current research focuses on developing robust federated learning algorithms, often incorporating neural tangent kernels, personalized models, and techniques like asynchronous SGD or federated averaging in random subspaces, to improve model accuracy and efficiency despite data heterogeneity and non-i.i.d. data. These advancements are crucial for enabling privacy-preserving collaborative learning in various applications, including medical imaging, IoT networks, and recommendation systems, where data is inherently decentralized and varied. The ultimate goal is to build effective and efficient machine learning models that can leverage the power of distributed data without compromising privacy or performance.

Papers

March 11, 2024

February 11, 2024

PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression
Jiahao Pang, Kevin Bui, Dong Tian
Point Cloud New Framework Point Cloud Compression Point Cloud Representation Heterogeneous Setting 3D Point

December 14, 2023

CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
Jiangming Shi, Shanshan Zheng, Xiangbo Yin, Yang Lu, Yuan Xie, Yanyun Qu
Contrastive Learning Long Tailed Data Heterogeneous Setting Federated Contrastive Learning

November 3, 2023

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces
Aditya Desai, Benjamin Meisburger, Zichang Liu, Anshumali Shrivastava
Recommendation System Collaborative Filtering Recommendation Model Federated Averaging Heterogeneous Setting Neural Collaborative Filtering Random Subspace

October 17, 2023

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control
Xianyue Peng, Hang Gao, Hao Wang, H. Michael Zhang
Reinforcement Learning Multi Agent Reinforcement Learning Traffic Signal Control Traffic Flow Platoon Control Heterogeneous Setting Congestion Mitigation Traffic Flow Theory

August 8, 2023

Heterogeneous 360 Degree Videos in Metaverse: Differentiated Reinforcement Learning Approaches
Wenhan Yu, Jun Zhao
Ubiquitous Semantic Metaverse Heterogeneous Setting Educational Video Scene Optimization Frame Structure

June 13, 2023

Privacy Preserving Bayesian Federated Learning in Heterogeneous Settings
Disha Makhija, Joydeep Ghosh, Nhat Ho
Privacy Policy Differential Privacy Guarantee Heterogeneous Setting Privacy Constraint Bayesian Federated Learning

March 15, 2023

Optimization Design for Federated Learning in Heterogeneous 6G Networks
Bing Luo, Xiaomin Ouyang, Peng Sun, Pengchao Han, Ningning Ding, Jianwei Huang
Artificial Intelligence Design Optimization G Network Edge Network Heterogeneous Setting Ubiquitous Intelligence AI Paradigm

January 11, 2023

Federated Learning under Heterogeneous and Correlated Client Availability
Angelo Rodio, Francescomaria Faticanti, Othmane Marfoq, Giovanni Neglia, Emilio Leonardi
Federated Learning Convergence Rate Heterogeneous Setting Client Availability

December 17, 2022

Physics-informed Neural Networks with Periodic Activation Functions for Solute Transport in Heterogeneous Porous Media
Salah A Faroughi, Ramin Soltanmohammad, Pingki Datta, Seyed Kourosh Mahjour, Shirko Faroughi
Physic Informed Neural Network Heterogeneous Setting Porous Medium Periodic Activation Function Solute Transport

September 21, 2022

FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization
Junjiao Tian, James Seale Smith, Zsolt Kira
Data Heterogeneity Heterogeneous Federated Learning Faster Convergence Heterogeneous Setting

July 17, 2022

Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR
Sannara Ek, Romain Rombourg, François Portet, Philippe Lalanda
Self Supervised Learning Semi Supervised Learning Continuum Limit Strong Baseline Heterogeneous Setting Federated Self Supervised Learning

April 28, 2022

Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features
Xinyi Shang, Yang Lu, Gang Huang, Hanzi Wang
Federated Setting Long Tailed Data Heterogeneous Setting Privacy Preserving Federated Learning Classifier Re Training

February 4, 2022

Machine Learning in Heterogeneous Porous Materials
Marta D'Elia, Hang Deng, Cedric Fraces, Krishna Garikipati, Lori Graham-Brady, Amanda Howard, George Karniadakis, Vahid Keshavarzzadeh, Robert M. Kirby, Nathan Kutz, Chunhui Li, Xing Liu, Hannah Lu, Pania Newell, Daniel O'Malley, Masa Prodanovic, Gowri Srinivasan, Alexandre Tartakovsky, Daniel M. Tartakovsky, Hamdi Tchelepi, Bozo Vazic, Hari Viswanathan, Hongkyu Yoon, Piotr Zarzycki
Machine Learning Material SCIence Heterogeneous Setting Novel Material Heterogeneous Material Porous Material

January 18, 2022

Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets
Anabik Pal, Zhiyun Xue, Sameer Antani
Large Scale Heterogeneous Setting

Heterogeneous Setting

Papers

Heterogeneous Image-based Classification Using Distributional Data Analysis

Advancing Graph Neural Networks with HL-HGAT: A Hodge-Laplacian and Attention Mechanism Approach for Heterogeneous Graph-Structured Data

PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression

CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control

Heterogeneous 360 Degree Videos in Metaverse: Differentiated Reinforcement Learning Approaches

Privacy Preserving Bayesian Federated Learning in Heterogeneous Settings

Optimization Design for Federated Learning in Heterogeneous 6G Networks

Federated Learning under Heterogeneous and Correlated Client Availability

Physics-informed Neural Networks with Periodic Activation Functions for Solute Transport in Heterogeneous Porous Media

FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization

Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR

Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features

Machine Learning in Heterogeneous Porous Materials

Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets