analiza aiqbench
This research addresses a critical bottleneck in vehicular AI by proposing a hierarchical federated learning framework that allows cars to perform diverse perception tasks while sharing only feature encoders. By decoupling global knowledge from task-specific models, the approach significantly improves accuracy and reduces communication overhead compared to standard single-task benchmarks. The work advances practical distributed machine learning for autonomous driving without requiring raw data centralization.
Encoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs
arXiv:2609.36157v1 Announce Type: new Abstract: Most federated learning frameworks for vehicular ad hoc networks assume that all vehicles collaboratively train a single model for a common task. This assumption limits their applicability to practical vehicular environments, where vehicles may perform heterogeneous but related perception tasks with different output spaces. This paper proposes encoder-sharing hierarchical multi-task federated learning (EN-HMTFL), which integrates cluster-based hierarchical federated learning with a globally shared encoder and vehicle-local decoders. EN-HMTFL enables vehicles performing different tasks to collaboratively learn a transferable feature representation while preserving their task-specific models locally. Only the encoder is exchanged and aggregated through the hierarchy, whereas raw data and local decoder parameters remain at the vehicles. The proposed framework is evaluated on the MNIST and GTSRB datasets in different vehicular scenarios. Across the evaluated scenarios, EN-HMTFL improves accuracy by up to 24.0% relative to the compared representation-sharing benchmark. In scenarios where EN-HMTFL converges earlier, the reduction reaches up to 69 communication rounds (28.8%).
Abstract:Most federated learning frameworks for vehicular ad hoc networks assume that all vehicles collaboratively train a single model for a common task. This assumption limits their applicability to practical vehicular environments, where vehicles may perform heterogeneous but related perception tasks with different output spaces. This paper proposes encoder-sharing hierarchical multi-task federated learning (EN-HMTFL), which integrates cluster-based hierarchical federated learning with a globally shared encoder and vehicle-local decoders. EN-HMTFL enables vehicles performing different tasks to collaboratively learn a transferable feature representation while preserving their task-specific models locally. Only the encoder is exchanged and aggregated through the hierarchy, whereas raw data and local decoder parameters remain at the vehicles. The proposed framework is evaluated on the MNIST and GTSRB datasets in different vehicular scenarios. Across the evaluated scenarios, EN-HMTFL improves accuracy by up to 24.0% relative to the compared representation-sharing benchmark. In scenarios where EN-HMTFL converges earlier, the reduction reaches up to 69 communication rounds (28.8%).
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Emerging Technologies (cs.ET); Systems and Control (eess.SY)
arXiv:2609.36157 [cs.LG]
(or arXiv:2609.36157v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.36157 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 188 cuvinte
Subiecte conexe
News
Quantum Computing Report · 25 iul. 2026
FedMust: Semi-supervised Multi-task Student-Teacher Federated Learning for Multi-organ CT Segmentation
arXiv · 22 sept. 2026
Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
arXiv · 20 iul. 2026
Building multi-Region visualizations with Highcharts in Amazon Quick
AWS · 23 iul. 2026