Federated Fuzzy Neural Network with Evolutionary Rule Learning

TL;DR

This paper introduces a federated fuzzy neural network with evolutionary rule learning that effectively manages non-IID data and uncertainties in distributed settings, enhancing generalization and personalization.

Contribution

It proposes a novel FedFNN framework with ERL that evolves and personalizes rules for each client, addressing non-IID data challenges in federated learning.

Findings

FedFNN outperforms existing methods on various datasets.

ERL improves rule relevance and model adaptability.

The approach enhances both generalization and personalization in federated settings.

Abstract

Distributed fuzzy neural networks (DFNNs) have attracted increasing attention recently due to their learning abilities in handling data uncertainties in distributed scenarios. However, it is challenging for DFNNs to handle cases in which the local data are non-independent and identically distributed (non-IID). In this paper, we propose a federated fuzzy neural network (FedFNN) with evolutionary rule learning (ERL) to cope with non-IID issues as well as data uncertainties. The FedFNN maintains a global set of rules in a server and a personalized subset of these rules for each local client. ERL is inspired by the theory of biological evolution; it encourages rule variations while activating superior rules and deactivating inferior rules for local clients with non-IID data. Specifically, ERL consists of two stages in an iterative procedure: a rule cooperation stage that updates global rules by aggregating local rules based on their activation statuses and a rule evolution stage that evolves the global rules and updates the activation statuses of the local rules. This procedure improves both the generalization and personalization of the FedFNN for dealing with non-IID issues and data uncertainties. Extensive experiments conducted on a range of datasets demonstrate the superiority of the FedFNN over state-of-the-art methods.