English

LINDT: Tackling Negative Federated Learning with Local Adaptation

Machine Learning 2020-11-24 v1 Distributed, Parallel, and Cluster Computing

Abstract

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.

Keywords

Cite

@article{arxiv.2011.11160,
  title  = {LINDT: Tackling Negative Federated Learning with Local Adaptation},
  author = {Hong Lin and Lidan Shou and Ke Chen and Gang Chen and Sai Wu},
  journal= {arXiv preprint arXiv:2011.11160},
  year   = {2020}
}
R2 v1 2026-06-23T20:26:01.428Z