提出隐私保护的联邦元学习框架，加速神经场建模且不泄露用户数据。
FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields
- 设计隐私约束损失函数，控制本地元优化中的数据泄露风险。
- 在少样本和非独立同分布数据下仍实现快速优化与高重建精度。
- 适合医疗、工业等敏感数据场景下的分布式神经场建模应用。
神经场提供了一种高效的数据表示方式，能有效处理多种模态和大规模数据。然而，训练神经场通常需要大量数据和计算资源，这对资源受限的边缘设备构成挑战。为应对这一问题，我们提出一种新型联邦元学习（FedMeNF）方法。该方法采用新的隐私保护损失函数，在本地元优化过程中抑制隐私泄露，使本地元学习器可快速高效地优化，同时无需保留客户端私有数据。实验表明，即使在少样本或非独立同分布数据条件下，FedMeNF仍能实现快速优化速度和鲁棒的重建性能，同时保障客户端数据隐私。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。