FedEdge-Adapt: Adaptive Federated Learning for Heterogeneous Edge AI Systems

DASFL: Dynamic Adaptive Split Federated Learning for Heterogeneous Clients

Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation

Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge. Federated knowledge distillation (FedKD) alleviates model heterogeneity by combining prototype-wise parameter aggregation and knowledge transfer across heterogeneous models. However, transmitting gradients still introduces considerable communication overhead, while existing compression approaches typically apply a uniform strategy across clients and ignore their diverse model characteristics and resource capacities. To address this issue, we propose a heterogeneous compression framework for FedKD that enables each client to select a compression strategy from a candidate strategy set. We formulate the compression strategy selection problem as a non-stationary stochastic multi-armed bandit (MAB), where each arm corresponds to a compression strategy. An efficiency-aware reward is designed by jointly considering local optimization improvement, global knowledge alignment, and execution time. Based on this formulation, we develop an Adaptive heterogeneouS Compression algorithm for fEderated kNowledge Distillation (ASCEND), which employs an exponential moving average (EMA)-enhanced $\epsilon$-greedy policy to balance exploration and exploitation. Experimental results on multiple datasets demonstrate that ASCEND effectively adapts to heterogeneous model and resource settings, reducing communication overhead and training time while maintaining competitive model accuracy.

FLEAT: Energy-Accuracy Trade-off in Federated Learning over Heterogeneous Edge Devices

—Federated Learning (FL) enables collaborative model training across edge devices but faces challenges balancing energy consumption, heterogeneous resources, and accuracy in IoT ecosystems. Existing solutions often overlook adaptive coordination of computation and communication or depend on hardware-level adjustments unavailable on constrained devices. We propose FLEAT (Federated Learning Energy and Accuracy Tuning), a framework that jointly optimizes energy efficiency and model accuracy via dynamic local update adaptation and gradient-informed layer-wise pruning. FLEAT introduces a theoretical error bound for synchronous FL under these mechanisms and employs an energy-aware optimization loop to allocate per-device computation/communication time. By scaling local updates to device capabilities and pruning redundant layers based on parameter importance, FLEAT mitigates stragglers, reduces communication overhead, and stabilizes convergence via normalized gradient aggregation. We evaluate FLEAT in both real-world IoT deployments and simulated edge networks. At a fixed wall-clock budget, FLEAT achieves a higher convergence rate—reaching higher accuracy earlier—than FedAvg, FedProx, and FedNova; when all methods train to completion, it remains within 1.2–3.1% of FedAvg’s final accuracy while cutting total energy by 16.2%. Relative to existing studies, FLEAT matches or surpasses their accuracy while strictly lowering energy, owing to its joint tuning of local steps and pruning under an energy-aware objective. This work bridges model-and system-level optimizations, offering a scalable solution for energy-accuracy equilibrium in heterogeneous FL deployments.

FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients

Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per deployment limit is costly. Federated supernet training instead learns one elastic model with differently sized subnetworks, then deploys a suitable one to each device. When client inference budgets differ, however, parameters exclusive to high-cost subnetworks are reachable by fewer clients. We propose FEAST, a federated shared-space training framework that counters this imbalance by jointly training multiple subnetworks within each client's limit. Budget-tailored sub-supernet routing sends only the relevant supernet portion, and sparse aggregation merges the returned parameter slices. The trained supernet directly serves the subnetworks used during federation and supports post-hoc extraction of additional subnetworks without federated retraining. We further show that independently assigning clients'training-data volumes and inference budgets can distort accuracy--inference-cost comparisons in heterogeneous FL simulations, and introduce a one-parameter $\gamma$-allocation protocol to control this coupling. In our experimental setup, the SuperFedNAS and DeepFedNAS supernet training procedures remain near chance at 25M and reach at most $17.09\%$ at $596$M inference MACs; FEAST reaches $71.06\%$ at $596$M, $2.4$ points above the strongest model-heterogeneous weight-sharing baseline at its largest tier. Across CIFAR-100, CINIC-10, and TinyImageNet-200, FEAST achieves the highest population-averaged accuracy among the evaluated weight-sharing methods when each client receives its largest affordable subnetwork. Sub-supernet routing reduces aggregate model-parameter traffic by $6.8\times$ relative to full-supernet transmission.

FedLEAF: Bi-directional Prototype Adaptation for Heterogeneous Federated Learning

Prototype-based knowledge sharing effectively mitigates data and model heterogeneity in federated learning (FL) by exchanging class-level semantic information. However, existing methods typically assume all local prototypes are equally reliable. Consequently, low-quality prototypes from heterogeneous models or dynamic clients can contaminate the global aggregation, leading to a vicious cycle of noise accumulation and performance degradation. To address this, we propose FedLEAF, a Federated Learning framework with server-side proactive Evaluation and clientside Adaptive Fusion. Specifically, the server employs an Adaptive Learning Prototypes (ALP) network to dynamically evaluate prototype reliability and generate learnable aggregation weights, ensuring that highquality prototypes exert a primary influence on the global model. Meanwhile, the client utilizes a Historical Consistency Fusion (HCF) strategy to selectively absorb global knowledge by assessing its consistency with locally maintained historical prototypes. Extensive experiments on standard datasets demonstrate that FedLEAF achieves effective improvements in model accuracy and robustness compared to existing methods.

Robust Federated Learning Under Real-World Client Churn

FeLiX is presented, an FL orchestration framework that minimizes wall-clock time-to-target accuracy on live interaction streams and achieves near-oracular performance in real-world settings.