Log In Sign Up

LINDT: Tackling Negative Federated Learning with Local Adaptation

by   Hong Lin, et al.

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.


page 1

page 2

page 3

page 4


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

Federated Learning (FL) has become an active and promising distributed m...

Addressing Heterogeneity in Federated Learning via Distributional Transformation

Federated learning (FL) allows multiple clients to collaboratively train...

Efficient Client Contribution Evaluation for Horizontal Federated Learning

In federated learning (FL), fair and accurate measurement of the contrib...

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...

A Bayesian Federated Learning Framework with Multivariate Gaussian Product

Federated learning (FL) allows multiple clients to collaboratively learn...

Heterogeneous Data-Aware Federated Learning

Federated learning (FL) is an appealing concept to perform distributed t...

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

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