Jul 2026· International Conference on Edge Computing [Services Society]· pp. 84-90· 0 citations· 17 references
Abstract
Federated distillation (FD) enables collaborative edge learning by exchanging soft predictions rather than model parameters, offering communication efficiency and architectural flexibility. However, deploying FD over heterogeneous wireless networks requires principled methods to schedule device participation and allocate upload volumes under per-round resource constraints. Existing approaches assume uniform participation or rely on heuristic selection, ignoring the coupling among communication cost, computational capability, and privacy posture across devices. This paper proposes KaaS-Edge, a Knowledge-as-a-Service framework that formulates device scheduling as budgeted submodular maximization. We derive an optimal water-filling volume allocation in closed form and present RADS (Resource-Aware Distillation Scheduling), a greedy algorithm with a constant-factor approximation guarantee. Experiments on CIFAR-100 demonstrate that KaaS-Edge achieves accuracy comparable to full-participation baselines while reducing per-round communication by nearly ten times and cumulative bandwidth by over an order of magnitude, with graceful degradation under stringent privacy constraints.
A degeneracy-aware resource allocation framework that casts multi-architecture orchestration as a probabilistic game and, unlike single-solution optimization, deliberately favors allocations realizable by many structurally distinct yet performance-equivalent strategy profiles is proposed.
A novel framework, termed DRL-RA, which synergistically integrates Deep Reinforcement Learning (DRL) with reliability-aware optimization with explicit reliability guarantees through cross-layer link reliability modeling, node availability estimation, and smooth reliability proxy functions is proposed.
Fei-Yan Bu, Zheng Wang, Yong Pan et al.· Computers, Materials & C...· 0 citations
Over-the-air FL with EH MDs under heterogeneous data distributions under heterogeneous data distributions is studied, and the proposed unified framework improves fairness or personalization, depending on the operating mode, while reducing communication overhead.
F. Bagci, Busra Tegin, Mohammad Kazemi et al.· 0 citations
This paper forms a privacy-aware offloading problem that jointly optimizes delay and energy while penalizing the theoretical privacy leakage of coded tasks under noisy leakage observations, and proposes a coded task offloading scheme for D2D networks under stochastic task arrivals and queue-based dynamics.
Diego Cajaraville-Aboy, M. Fernández-Veiga, A. Fernández-Vilas et al.· arXiv.org· 0 citations
This work proposes 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, offering a scalable solution for energy-accuracy equilibrium in heterogeneous FL deployments.
Javad Dogani, Reza Namvar, Masoumeh Khodarahmi et al.· IEEE Transactions on Mobile...· 0 citations
AF-EdgeRL is proposed, a novel Byzantine-resilient Asynchronous Federated Reinforcement Learning framework tailored for distributed resource allocation and dynamic task offloading and establishes theoretical convergence guarantees under non-convex reinforcement learning objectives.
Daniel Merrow, Tember L. Nair, Lucas Farnandez· International Journal of App...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
