DeepAI
Log In Sign Up

LINDT: Tackling Negative Federated Learning with Local Adaptation

11/23/2020
by   Hong Lin, et al.
0

Federated Learning (FL) is a promising distributed learning paradigm, which allows a number of data owners (also called clients) to collaboratively learn a shared model without disclosing each client's data. However, FL may fail to proceed properly, amid a state that we call negative federated learning (NFL). This paper addresses the problem of negative federated learning. We formulate a rigorous definition of NFL and analyze its essential cause. We propose a novel framework called LINDT for tackling NFL in run-time. The framework can potentially work with any neural-network-based FL systems for NFL detection and recovery. Specifically, we introduce a metric for detecting NFL from the server. On occasion of NFL recovery, the framework makes adaptation to the federated model on each client's local data by learning a Layer-wise Intertwined Dual-model. Experiment results show that the proposed approach can significantly improve the performance of FL on local data in various scenarios of NFL.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/23/2021

Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning

Federated Learning (FL) has become an active and promising distributed m...
10/26/2022

Addressing Heterogeneity in Federated Learning via Distributional Transformation

Federated learning (FL) allows multiple clients to collaboratively train...
02/26/2021

Efficient Client Contribution Evaluation for Horizontal Federated Learning

In federated learning (FL), fair and accurate measurement of the contrib...
10/16/2020

Flow-FL: Data-Driven Federated Learning for Spatio-Temporal Predictions in Multi-Robot Systems

In this paper, we show how the Federated Learning (FL) framework enables...
02/03/2021

A Bayesian Federated Learning Framework with Multivariate Gaussian Product

Federated learning (FL) allows multiple clients to collaboratively learn...
11/12/2020

Heterogeneous Data-Aware Federated Learning

Federated learning (FL) is an appealing concept to perform distributed t...
11/17/2022

FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data

Federated learning is a distributed learning that allows each client to ...