Metraipolis › archive › dc_bf2902914f14
Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation — arXiv:2608.15660
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15660
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:02:06.929Z
- SHA-256 of the archived text
06a1e98f65f2c1d2e084942cecf2422b066092b12ce25b20529278cfa5ad4bf5- Stable URL of this page
https://metraipolis.com/documento/dc_bf2902914f14
How to cite
Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation — arXiv:2608.15660 — arXiv (en), https://arxiv.org/abs/2608.15660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf2902914f14 (Metraipolis archive dc_bf2902914f14, sha256 06a1e98f65f2c1d2e084942cecf2422b066092b12ce25b20529278cfa5ad4bf5)
BibTeX
@misc{dcbf2902914f14,
title = {Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation — arXiv:2608.15660},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15660},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf2902914f14; sha256 06a1e98f65f2c1d2e084942cecf2422b066092b12ce25b20529278cfa5ad4bf5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-18 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.15660 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T18:07:16.073Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).