Federated fine‑tuning of large language models (LLMs) over mobile radio access networks (RANs) creates recurring, deadline‑sensitive communication workloads that are currently treated as independent device‑originated flows by transport networks. This mismatch hinders efficient resource provisioning, especially for optical circuit switching and all‑photonics transport that require predictable traffic. The paper proposes that future RANs act as learning‑aware traffic shapers, aggregating asynchronous user‑equipment updates at the gNB to produce fewer, bounded‑size transfers that can be scheduled on dynamically provisioned optical links, thereby combining packet‑based access flexibility with programmable transport capacity.
arXiv:2410. 05662v4 Announce Type: replace Abstract: Most federated learning (FL) approaches assume a fixed device set.
arXiv:2411. 02908v2 Announce Type: replace Abstract: Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distributed training.
arXiv:2609.15763v1 Announce Type: cross Abstract: Federated continual learning (FCL) enables shared global models to continuously adapt to distributed and non-stationary data streams, making it impor...
FedSAP is a federated learning framework that addresses heterogeneous edge devices by using structured pruning as a budget-constrained tri-state channel allocation. It partitions model channels into a Global pool, pseudo-domain-specific Private pools, and a Dropped state, allowing broadly useful features to be shared while isolating domain-sensitive updates. Experiments on Digits and Office-Caltech datasets show FedSAP achieving higher mean global accuracy than the strongest baseline while supporting up to 80% client pruning ratios.
arXiv:2606. 03664v1 Announce Type: cross Abstract: Ultra Reliable and Low Latency Communications (URLLC) was one of the main motivations behind 5G, with 3GPP advertising 1-10 ms latency targets for applications such as industrial automation, Vehicle-To-Everything (V2X), tactical edge networking, and unmanned-system control.
arXiv:2607. 13119v1 Announce Type: cross Abstract: In standard federated learning systems, the parameter server broadcasts the global model to the participating devices in every iteration.
arXiv:2609.24455v1 Announce Type: cross Abstract: Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. Howeve...
The paper introduces FedQoS, an asynchronous federated learning framework designed for multimodal in‑cabin interaction in smart vehicles. It uses a two‑phase gating mechanism: a resource‑aware training gate that starts local learning only when sensing buffers and energy reserves meet safety thresholds, and a QoS‑aware transmission policy that gates uplink updates based on an efficiency score balancing model novelty, latency, and energy costs. Experiments on vehicular datasets show FedQoS achieves competitive personalized accuracy with only marginal loss compared to FedAvg, while reducing communication overhead by 76.7% and latency cost by 26.0%.
arXiv:2606. 28342v1 Announce Type: cross Abstract: Decentralized learning is a promising paradigm for collaborative training in mobile and pervasive systems, as it avoids a central coordinator and does not require sharing raw data.
MANE is a distributed inference framework that uses a multi‑path tail architecture to allow dynamic accuracy–throughput trade‑offs during edge onloading of deep neural networks. It introduces a novel multi‑path model, a three‑stage training scheme with Joint Head Network Distillation loss, and a hysteresis‑based scheduler with an equitable device‑fallback policy. The system achieves over 80% SLO satisfaction and 6pp higher accuracy than on‑device alternatives while supporting up to 40 concurrent devices.
The paper introduces COMLLM, a generative framework that combines Group Relative Policy Optimization with a Look‑Ahead Collaborative Simulation to enable multi‑turn reasoning for task offloading in Mobile Edge Computing. By performing multi‑step Monte Carlo rollouts that jointly model server queue dynamics, COMLLM incorporates long‑term system evolution into its reward design, achieving near‑optimal latency and improved load‑balancing fairness. The framework demonstrates zero‑shot scalability to larger network topologies, outperforming supervised fine‑tuning, deep reinforcement learning, and heuristic baselines without requiring retraining.
arXiv:2608. 01426v1 Announce Type: new Abstract: Federated learning (FL) enables distributed optimization and learning across decentralized edge devices while preserving data privacy, but its performance is fundamentally constrained by heterogeneous data distributions, limited communication resources, and energy availability.