Hierarchical Aggregation and Cooperative Caching for Decentralized Federated Learning in UAV-Assisted Internet of Vehicles

Abstract

Decentralized federated learning (DFL) and efficient content delivery are critical in uncrewed aerial vehicle (UAV)-assisted Internet of Vehicles (IoV). However, the performance is hampered by dynamic topology, energy constraints, and fluctuating computational loads. In this article, we present a unified optimization framework that reuses the DFL aggregation structure for cooperative edge caching in UAV-assisted IoV. In the first stage, we formalize the hierarchical DFL aggregation route as an NP-hard combinatorial problem and solve it with a graph neural network (GNN)-enhanced proximal policy optimization (PPO) algorithm for aggregation route (GPPO-R), which rapidly converges to near-optimal routing structures and achieves the tradeoff balance between synchronization latency and energy consumption. In the second stage, we design a DFL-based multiagent PPO caching strategy (DFL-MAPPO) that leverages the DFL aggregation structure and neighbor-state sharing. It consists of two phases: a long short-term memory (LSTM)-driven proactive caching phase, where the LSTM model is trained via DFL. A real-time multiagent reinforcement learning (MARL) phase for dynamic cache adjustment. Extensive simulations across varying number of UAVs, cache capacities, and user loads demonstrate that GPPO-R and DFL-MAPPO jointly reduce request latency and energy overhead compared to independent variants and classical schemes. The results validate the effectiveness and scalability of the proposed framework in dynamic UAV networks, providing a robust solution for integrated model aggregation and content caching in IoV.