Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange

2022-08-04 · Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Mung Chiang, Christopher G. Brinton

Federated learning (FL) has been recognized as one of the most promising solutions for distributed machine learning (ML). In most of the current literature, FL has been studied for supervised ML tasks, in which edge devices collect labeled data. Nevertheless, in many applications, it is impractical to assume existence of labeled data across devices. To this end, we develop a novel methodology, Cooperative Federated unsupervised Contrastive Learning (CF-CL), for FL across edge devices with unlabeled datasets. CF-CL employs local device cooperation where data are exchanged among devices through device-to-device (D2D) communications to avoid local model bias resulting from non-independent and identically distributed (non-i.i.d.) local datasets. CF-CL introduces a push-pull smart data sharing mechanism tailored to unsupervised FL settings, in which, each device pushes a subset of its local datapoints to its neighbors as reserved data points, and pulls a set of datapoints from its neighbors, sampled through a probabilistic importance sampling technique. We demonstrate that CF-CL leads to (i) alignment of unsupervised learned latent spaces across devices, (ii) faster global convergence, allowing for less frequent global model aggregations; and (iii) is effective in extreme non-i.i.d. data settings across the devices.

📄 PDF Abstract BibTeX arXiv:2208.02856

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning Federated Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

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

2024-04-15 · Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Christopher G. Brinton

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 labe…

Contrastive Learning Federated Learning

Heterogeneous Federated Learning Systems for Time-Series Power Consumption Prediction with Multi-Head Embedding Mechanism

2025-01-21 · Jia-Hao Syu, Jerry Chun-Wei Lin, Gautam Srivastava, Unil Yun

Time-series prediction is increasingly popular in a variety of applications, such as smart factories and smart transportation. Researchers have used various techniques to predict power consumption, but existing models la…

Federated Learning Network Embedding Time Series Time Series Prediction+1

Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients

2024-05-25 · Farhad Pourpanah, Mahdiyar Molahasani, Milad Soltany, Michael Greenspan 외

We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised feder…

Domain Generalization Federated Learning

Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning

2024-02-15 · Seohyun Lee, Anindya Bijoy Das, Satyavrat Wagle, Christopher G. Brinton

One of the main challenges of decentralized machine learning paradigms such as Federated Learning (FL) is the presence of local non-i.i.d. datasets. Device-to-device transfers (D2D) between distributed devices has been s…

Federated Learning reinforcement-learning Reinforcement Learning

Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings

2026-04-12 · Cristiano Mafuz, Rodrigo Silva arxiv

Federated learning (FL) performance is highly sensitive to heterogeneity across clients, yet practitioners lack reliable methods to anticipate how a federation will behave before training. We propose readiness indices, d…

Federated Learning