Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis

Abstract

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task.

arXiv comment46 pages, 9 figures, to appear in IEEE J. Sel. Areas Commun

References in corpus (13)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Federated Learning: Challenges, Methods, and Future Directions
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
• Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
• Sparsified SGD with Memory
• BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
• Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
• D${}^2$: Decentralized Training over Decentralized Data
• Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
• Over-the-air Function Computation in Sensor Networks
• SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Stochastic Optimization
• Optimized Power Control Design for Over-the-Air Federated Edge Learning
• An introduction to decentralized stochastic optimization with gradient tracking

Cited by in corpus (2)

• Channel-Driven Monte Carlo Sampling for Bayesian Distributed Learning in Wireless Data Centers
• Bayesian Variational Federated Learning and Unlearning in Decentralized Networks