FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 56 of its 71 references that are in the map. First posted on arXiv 8 Aug 2025.
Builds on
56 of 71 references.
References · 56
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2016Deep Learning with Differential Privacycited by 2,728
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2018On First-Order Meta-Learning Algorithmscited by 1,018
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
38 more
- 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
- 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
- 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
- 2020State of the Art on Neural Renderingcited by 278
- 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
- 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
- 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
- 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
- 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
- 2016Concentrated Differential Privacycited by 144
- 2020Adversarial Generation of Continuous Imagescited by 135
- 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
- 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
- 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
- 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
- 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 69
- 2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
- 2023AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesiscited by 49
- 2023Bounding Training Data Reconstruction in DP-SGDcited by 46
- 2022pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learningcited by 44
- 2019Differentially Private Meta-Learningcited by 41
- 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
- 2022Generalizable Implicit Neural Representations via Instance Pattern Composerscited by 39
- 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 36
- 2020Privacy-preserving Collaborative Learning with Automatic Transformation Searchcited by 31
- 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
- 2022Communication-Efficient Federated Learning with Accelerated Client Gradientcited by 24
- 2019GolfDB: A Video Database for Golf Swing Sequencingcited by 21
- 2023Locality-Aware Generalizable Implicit Neural Representationcited by 16
- 2024PetFace: A Large-Scale Dataset and Benchmark for Animal Identificationcited by 16
- 2023Learning Large-scale Neural Fields via Context Pruned Meta-Learningcited by 13
- 2024Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learningcited by 12
- 2022Provable Generalization of Overparameterized Meta-learning Trained with SGDcited by 9
- 2022Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fieldscited by 9
- 2023Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fieldscited by 8
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.