FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields

TL;DR

FedMeNF is a novel federated meta-learning method that enhances neural fields by ensuring privacy preservation, enabling fast, efficient, and robust data reconstruction across diverse modalities with limited data and privacy concerns.

Contribution

The paper introduces FedMeNF, a privacy-preserving federated meta-learning approach that improves neural fields training on resource-constrained devices while safeguarding client data.

Findings

Achieves fast optimization and robust reconstruction

Handles few-shot and non-IID data effectively

Preserves client data privacy

Abstract

Neural fields provide a memory-efficient representation of data, which can effectively handle diverse modalities and large-scale data. However, learning to map neural fields often requires large amounts of training data and computations, which can be limited to resource-constrained edge devices. One approach to tackle this limitation is to leverage Federated Meta-Learning (FML), but traditional FML approaches suffer from privacy leakage. To address these issues, we introduce a novel FML approach called FedMeNF. FedMeNF utilizes a new privacy-preserving loss function that regulates privacy leakage in the local meta-optimization. This enables the local meta-learner to optimize quickly and efficiently without retaining the client's private data. Our experiments demonstrate that FedMeNF achieves fast optimization speed and robust reconstruction performance, even with few-shot or non-IID data across diverse data modalities, while preserving client data privacy.