Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.06301 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913980479438848 |
|---|---|
| author | Yun, Junhyeog Hong, Minui Kim, Gunhee |
| author_facet | Yun, Junhyeog Hong, Minui Kim, Gunhee |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06301 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields Yun, Junhyeog Hong, Minui Kim, Gunhee Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing 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. |
| title | FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2508.06301 |