Energy Efficient Federated Learning with Hyperdimensional Computing over Wireless Communication Networks

2026-02-25

AI Summary

This work addresses the challenges of high energy consumption, substantial computational overhead, and privacy preservation in federated learning (FL) over wireless edge networks by proposing FL-HDC-DP, an energy-efficient framework that integrates hyperdimensional computing (HDC) with differential privacy (DP). The approach introduces HDC into FL for the first time, reducing local training to lightweight hypervector operations and establishing an analytical model that characterizes the relationship between HDC dimensionality and convergence rounds. Building on this model, the framework jointly optimizes HDC dimension, transmission time, bandwidth, transmit power, and CPU frequency to minimize total energy consumption under rigorous DP privacy constraints. Experimental results demonstrate that FL-HDC-DP reduces total energy consumption by up to 83.3% compared to conventional neural network–based FL baselines and achieves 90% model accuracy in approximately 3.5× fewer communication rounds.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

In this paper, we investigate a problem of minimizing total energy consumption for secure federated learning (FL) over wireless edge networks. To address the high computational cost and privacy challenges in conventional FL with neural networks (NN) for resource-constrained users, we propose a novel FL with hyperdimensional computing and differential privacy (FL-HDC-DP) framework. In the considered model, each edge user employs hyperdimensional computing (HDC) for local training, which replaces complex neural updates with simple hypervector operations, and applies differential privacy (DP) noise to protect transmitted model information. We optimize the total energy of computation and communication under both latency and privacy constraints. We formulate the problem as an optimization that minimizes the total energy of all users by jointly allocating HDC dimension, transmission time, system bandwidth, transmit power, and CPU frequency. To solve this problem, a sigmoid-variant function is proposed to characterize the relationship between the HDC dimension and the convergence rounds required to reach a target accuracy. Based on this model, we develop two alternating optimization algorithms, where closed-form expressions for time, frequency, bandwidth, and power allocations are derived at each iteration. Since the iterative algorithm requires a feasible initialization, we construct a feasibility problem and obtain feasible initial resource parameters by solving a per round transmission time minimization problem. Simulation results demonstrate that the proposed FL-HDC-DP framework achieves up to 83.3% total energy reduction compared with the baseline, while attaining about 90% accuracy in approximately 3.5X fewer communication rounds than the NN baseline.

Problem

• Federated Learning
• Energy Efficiency
• Hyperdimensional Computing
• Differential Privacy
• Wireless Edge Networks

Innovation

• Hyperdimensional Computing
• Federated Learning
• Energy Efficiency
• Differential Privacy
• Wireless Edge Networks