| Liu, Jing, Yang, Kun, Wang, Yan, Yang, Dingkang, Hao, Xiaoshuai, Zhang, Wei, Liu, Yang and Zhou, Wei 2026. PFAdapter: Hierarchical LoRA decomposition for personalized federated MLLMs. IEEE Transactions on Cognitive Communications and Networking 10.1109/tccn.2026.3740672 |
Abstract
Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges. Within distributed network environments, Multimodal Large Language Models (MLLMs) serve as cognitive engines for edge devices, yet federated fine-tuning faces substantial challenges in balancing global knowledge aggregation with local adaptation under heterogeneous network conditions. Conventional federated protocols typically rely on uniform parameter aggregation, which conflates domain-invariant features with client-specific nuances, thereby resulting in suboptimal personalization and excessive communication overhead. To address these challenges, we propose PFAdapter, a communication-efficient framework introducing hierarchical LoRA decomposition to explicitly separate adapter parameters into global-shared and local-private components. Query and key projections are assigned to global synchronization for capturing universal multimodal semantics across the network, while value and output projections remain localized for edge-specific adaptation. Additionally, orthogonality regularization based on the Frobenius norm enforces strict separation between these components, preventing redundant feature learning. Selective aggregation protocols synchronize only global-shared components across the federated network, preserving local expertise and reducing communication costs by nearly 50%. Experiments on medical VQA and social multimodal benchmarks show that PFAdapter consistently improves over matched federated LoRA baselines while nearly halving synchronized adapter traffic. Empirical results indicate that projection-level decomposition offers a practical path toward communication-efficient agentic MLLM deployment in resource-constrained edge networks.
| Item Type: | Article |
|---|---|
| Date Type: | Published Online |
| Status: | In Press |
| Schools: | Schools > Computational & Mathematical Sciences Schools > Computer Science & Informatics |
| Publisher: | Institute of Electrical and Electronics Engineers |
| ISSN: | 2332-7731 |
| Last Modified: | 12 Oct 2026 12:00 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/190153 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions