mlsanityData to 14 Oct 2026

Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels

arXiv 2404.09861 ↗First posted 15 Apr 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 textitsmart 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 15 Apr 2024.

Builds on

32 of 53 references.

References · 32

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2018Federated Learning with Non-IID Datacited by 1,108
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  9. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  10. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  11. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
  12. 2020Federated Unsupervised Representation Learningcited by 93
20 more
  1. 2014Stochastic Optimization with Importance Samplingcited by 91
  2. 2022Divergence-aware Federated Self-Supervised Learningcited by 73
  3. 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 51
  4. 2021Federated Learning Meets Natural Language Processing: A Surveycited by 43
  5. 2020Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog Networkscited by 42
  6. 2021Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementationcited by 40
  7. 2016Importance Sampling for Minibatchescited by 36
  8. 2019Federated User Representation Learningcited by 32
  9. 2022Federated Learning for Privacy Preservation in Smart Healthcare Systems: A Comprehensive Surveycited by 31
  10. 2020Optimal Importance Sampling for Federated Learningcited by 20
  11. 2022Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clientscited by 20
  12. 2021FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentationcited by 19
  13. 2022Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networkscited by 18
  14. 2017Learning-Based Computation Offloading for IoT Devices with Energy Harvestingcited by 15
  15. 2021Federated Few-Shot Learning with Adversarial Learningcited by 11
  16. 2021FedCon: A Contrastive Framework for Federated Semi-Supervised Learningcited by 11
  17. 2023Towards Cooperative Federated Learning over Heterogeneous Edge/Fog Networkscited by 8
  18. 2020Can we Generalize and Distribute Private Representation Learning?cited by 5
  19. 2022Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchangecited by 5
  20. 2021An Optimal Relay Scheme for Outage Minimization in Fog-based Internet-of-Things (IoT) Networkscited by 1

Built on by

Not cited yet.