HongAvg: Hierarchical On-Demand Cognitive Split Federated Learning for Twin Agent Orchestration

Task-oriented Framework for Communication-Efficient Federated Learning: From Isolated Optimization to Holistic Synergy

Communication bottlenecks remain a primary obstacle to the large-scale deployment of federated learning (FL). This article proposes a comprehensive framework for building communication-efficient FL, founded on three fundamental pillars: model compression, client selection, and resource allocation. We first survey state-of-the-art techniques for each pillar, specifically elucidating how quantization, pruning, and low-rank approximation reduce payloads; how intelligent client schedulers exploit heterogeneity; and how emerging communication paradigms such as Integrated Sensing and Communication (ISAC) and Over-the-Air Computation (AirComp) redefine bandwidth and energy utilization. Subsequently, these insights are unified through a task-oriented design philosophy that couples strategy selection with cross-layer, multi-objective optimization. To validate the proposed framework, we present an autonomous driving case study with two complementary experiments: a task-oriented client scheduling strategy that improves object detection accuracy under the same communication time budget, and a joint quantization-bandwidth optimization that further reduces total training time under dynamic networks. Together, the experiments demonstrate the advantages of holistic task-oriented design for real-world FL deployment.

Toward Federated Cognitive Digital Twins over the Edge-to-Cloud Continuum

A Federated Cognitive Digital Twin (FCDT) architecture that combines federation and cognition within a unified approach improves scalability, responsiveness, and decision-making in complex distributed CPSs.

Digital Twin-Assisted Intent-Driven Autonomous Virtual Network Function Orchestration Using Federated Intelligence for Resilient 6G Networks

The 6G networks require autonomous and smart management of resources to support ultra-dense devices, dynamic traffic and low-latency services. The classic methods of Network Function Virtualization (NFV) orchestration utilize primarily the use of either a static or heuristics algorithm, which constrains their capacity to adjust to the dynamically evolving network conditions. Additionally, the current digital twin and distributed learning systems are characterized by a high level of synchronization overhead and poor automation abilities. To cope with these issues, this paper suggests a Federated Intelligence-based Digital Twin-Assisted Intent-Directed Autonomous Virtual Network Function (VNF) Orchestration. The proposed methodology combines the idea of digital twins to represent a real-time network with the idea of federated learning so that one can train models using a set of distributed edge nodes and maintain data privacy. In Python, the machine learning model is applied to interpret the network traffic data and forecast the demands of resources to be efficient in the orchestration of VNF. The experimental findings indicate that the suggested framework with such a high prediction precision of about 98, a higher usage of resources and a lower latency rate. The paper concluded that incorporating digital twins and federated intelligence could be useful in future 6G networks management to achieve high degrees of automation, scalability, and resilience.

HybridFLow: SDN-Orchestrated Client Partitioning for Hybrid Federated Learning

Cross-silo Federated Learning (FL) enables geographically distributed institutions to collaboratively train machine learning models without sharing raw data. In wide-area deployments, however, communication delays often dominate round completion time and exacerbate the straggler effect. Hybrid FL addresses this challenge by combining synchronous and asynchronous client participation, but effective partitioning requires visibility into network conditions such as shared bottlenecks, link utilization, and path contention that individual clients cannot observe. We present HybridFLow, a closed-loop SDN-driven orchestration framework that integrates network-layer intelligence directly into hybrid FL. Leveraging the SDN controller's global topology view, HybridFLow generates calibrated per-client communication-time estimates before each training round and uses them to partition clients into synchronous and asynchronous groups while balancing round latency and update staleness. After each round, measured communication times are fed back to the controller to continuously refine future predictions. Experimental results across multiple network topologies show that HybridFLow reaches 80% target accuracy 33-40% faster than SmartFLow and reduces average round duration by 30-40 seconds, while FedAsync fails to reach the target accuracy under non-IID data distributions.

Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication

Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing topology-agnostic aggregation into heterogeneous, multi-task environments creates a fundamental bottleneck: it drives negative transfer and overconsensus bias (OCB). This paper introduces a personalized DSC framework that cuts off this cross-task interference. At the node level, a policy-driven multi-path routing mechanism separates task-specific features from shared representations to preserve local fidelity. Across the network, we deploy a"communicationwhile- aggregation"protocol. It calibrates a column-stochastic consensus matrix using task affinities. This limits the system to absorbing complementary knowledge while actively blocking mismatched parameter updates. To bound the convergence, we derive a unified Lyapunov drift analysis. We reveal a strict Ushaped trade-off: deeper topological mixing reduces variance but amplifies structural OCB. Resolving this tension yields a closed-form expression for the optimal aggregation depth. We evaluate the proposed framework on NYU-v2, where the results reveal a clear trade-off between insufficient aggregation and excessive topological mixing. At the analytically derived optimal aggregation depth, our method achieves a 4.77% global relative improvement over the no-aggregation baseline and outperforms decentralized FedAvg, FedAMP, and heuristic max aggregation. We further evaluate the framework on Taskonomy and imperfect wireless links to examine the effects of network-size variation and wireless-link reliability.

DASFL: Dynamic Adaptive Split Federated Learning for Heterogeneous Clients