One Shot Aggregation

One-shot aggregation in machine learning focuses on efficiently combining data or model updates from multiple sources in a single round, minimizing communication overhead and latency. Current research emphasizes developing robust aggregation methods that are resilient to data heterogeneity and potential failures in distributed settings, exploring techniques like layer-wise posterior aggregation and novel convex optimization approaches. These advancements are crucial for improving the scalability and efficiency of federated learning, distributed training of large models, and other applications requiring efficient data fusion from diverse sources, particularly in resource-constrained environments like edge computing.

Papers

May 25, 2024

Analytic Federated Learning
Huiping Zhuang, Run He, Kai Tong, Di Fang, Han Sun, Haoran Li, Tianyi Chen, Ziqian Zeng
Numerical Aggregation One Shot Aggregation Analytic Learning

September 30, 2023

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
Xiang Liu, Liangxi Liu, Feiyang Ye, Yunheng Shen, Xia Li, Linshan Jiang, Jialin Li
Training Data Distribution One Shot Federated Learning One Shot Aggregation

May 31, 2023

Graph Entropy Minimization for Semi-supervised Node Classification
Yi Luo, Guangchun Luo, Ke Qin, Aiguo Chen
Graph Neural Network Node Classification Semi Supervised Node Classification Non Parametric Entropy Optimization One Shot Aggregation

February 12, 2023

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
Hamidreza Almasi, Harsh Mishra, Balajee Vamanan, Sathya N. Ravi
Training Data Potential Scalability Convex Optimization Convergence Guarantee Subspace Learning Country Recognition Planning Loss Byzantine Robust Aggregation Byzantine Failure One Shot Aggregation

April 16, 2022

Towards cost-effective and resource-aware aggregation at Edge for Federated Learning
Ahmad Faraz Khan, Yuze Li, Xinran Wang, Sabaat Haroon, Haider Ali, Yue Cheng, Ali R. Butt, Ali Anwar
Extreme Edge Resource Constrained Edge Edge Application One Shot Aggregation

April 3, 2022

Meta-Learning Approaches for a One-Shot Collective-Decision Aggregation: Correctly Choosing how to Choose Correctly
Hilla Shinitzky, Yuval Shahar, Ortal Parpara, Michal Ezrets, Raz Klein
Meta Learning Collective Decision Making Aggregation Method Aggregation Strategy Collective Decision One Shot Aggregation

February 2, 2022

3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation
Peter Richtárik, Igor Sokolov, Ilyas Fatkhullin, Elnur Gasanov, Zhize Li, Eduard Gorbunov
Training Data Error Feedback Communication Efficient Nonconvex Optimization Communication Complexity Point Transformer Gradient Communication One Shot Aggregation

One Shot Aggregation

Papers

Analytic Federated Learning

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation

Graph Entropy Minimization for Semi-supervised Node Classification

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization

Towards cost-effective and resource-aware aggregation at Edge for Federated Learning

Meta-Learning Approaches for a One-Shot Collective-Decision Aggregation: Correctly Choosing how to Choose Correctly

3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation