Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914755343548416 |
|---|---|
| author | Wagle, Satyavrat Hosseinalipour, Seyyedali Khosravan, Naji Brinton, Christopher G. |
| author_facet | Wagle, Satyavrat Hosseinalipour, Seyyedali Khosravan, Naji Brinton, Christopher G. |
| contents | Federated learning (FL) is a popular solution for distributed machine learning (ML). While FL has traditionally been studied for supervised ML tasks, in many applications, it is impractical to assume availability of labeled data across devices. To this end, we develop Cooperative Federated unsupervised Contrastive Learning ({\tt CF-CL)} to facilitate FL across edge devices with unlabeled datasets. {\tt CF-CL} employs local device cooperation where either explicit (i.e., raw data) or implicit (i.e., embeddings) information is exchanged through device-to-device (D2D) communications to improve local diversity. Specifically, we introduce a \textit{smart information push-pull} methodology for data/embedding exchange tailored to FL settings with either soft or strict data privacy restrictions. Information sharing is conducted through a probabilistic importance sampling technique at receivers leveraging a carefully crafted reserve dataset provided by transmitters. In the implicit case, embedding exchange is further integrated into the local ML training at the devices via a regularization term incorporated into the contrastive loss, augmented with a dynamic contrastive margin to adjust the volume of latent space explored. Numerical evaluations demonstrate that {\tt CF-CL} leads to alignment of latent spaces learned across devices, results in faster and more efficient global model training, and is effective in extreme non-i.i.d. data distribution settings across devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09861 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels Wagle, Satyavrat Hosseinalipour, Seyyedali Khosravan, Naji Brinton, Christopher G. Machine Learning Federated learning (FL) is a popular solution for distributed machine learning (ML). While FL has traditionally been studied for supervised ML tasks, in many applications, it is impractical to assume availability of labeled data across devices. To this end, we develop Cooperative Federated unsupervised Contrastive Learning ({\tt CF-CL)} to facilitate FL across edge devices with unlabeled datasets. {\tt CF-CL} employs local device cooperation where either explicit (i.e., raw data) or implicit (i.e., embeddings) information is exchanged through device-to-device (D2D) communications to improve local diversity. Specifically, we introduce a \textit{smart information push-pull} methodology for data/embedding exchange tailored to FL settings with either soft or strict data privacy restrictions. Information sharing is conducted through a probabilistic importance sampling technique at receivers leveraging a carefully crafted reserve dataset provided by transmitters. In the implicit case, embedding exchange is further integrated into the local ML training at the devices via a regularization term incorporated into the contrastive loss, augmented with a dynamic contrastive margin to adjust the volume of latent space explored. Numerical evaluations demonstrate that {\tt CF-CL} leads to alignment of latent spaces learned across devices, results in faster and more efficient global model training, and is effective in extreme non-i.i.d. data distribution settings across devices. |
| title | Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.09861 |