Adaptive Aggregation

Adaptive aggregation techniques aim to improve the efficiency and robustness of various machine learning and data processing tasks by intelligently combining information from multiple sources. Current research focuses on developing algorithms that dynamically weight or select contributing elements based on factors like data heterogeneity, model divergence, or task-specific relevance, employing methods such as attention networks and divergence-based weighting schemes. These advancements are impacting diverse fields, including federated learning (improving model convergence and resilience to attacks), neural network training (enhancing efficiency and performance of convolutional networks), and time series analysis (allowing for efficient symbolic representation and compression). The ultimate goal is to create more efficient, accurate, and reliable systems across a range of applications.

Papers

July 14, 2024

A3S: A General Active Clustering Method with Pairwise Constraints
Xun Deng, Junlong Liu, Han Zhong, Fuli Feng, Chen Shen, Xiangnan He, Jieping Ye, Zheng Wang
Semi Supervised Clustering Clustering Performance Adaptive Clustering Clustering Based Active Learning Pairwise Constraint Adaptive Aggregation

September 4, 2023

DRAG: Divergence-based Adaptive Aggregation in Federated learning on Non-IID Data
Feng Zhu, Jingjing Zhang, Shengyun Liu, Xin Wang
Raw Data Local Gradient Superlinear Convergence Adaptive Aggregation

May 17, 2023

Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network
Wenzhao Zhao, Barbara D. Wichtmann, Steffen Albert, Angelika Maurer, Frank G. Zöllner, Ulrike Attenberger, Jürgen Hesser
Monte Carlo Equivariant Network Equivariant Neural Network Max Filter Group Convolution Group Equivariant Adaptive Aggregation

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 7, 2023

Adaptive Aggregation for Safety-Critical Control
Huiliang Zhang, Di Wu, Benoit Boulet
Reinforcement Learning Safe Reinforcement Learning Human SAFETY Safety Critical Control Adaptive Aggregation

January 14, 2022

An efficient aggregation method for the symbolic representation of temporal data
Xinye Chen, Stefan Güttel
Time Series Temporal Data Symbolic Representation Time Series Representation Aggregation Method Adaptive Aggregation

December 16, 2021

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
Boqiang Xu, Jian Liang, Lingxiao He, Zhenan Sun
Generalizable Person Re Identification Domain Network Adaptive Aggregation

Adaptive Aggregation

Papers

A3S: A General Active Clustering Method with Pairwise Constraints

DRAG: Divergence-based Adaptive Aggregation in Federated learning on Non-IID Data

Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network

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

Adaptive Aggregation for Safety-Critical Control

An efficient aggregation method for the symbolic representation of temporal data

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification