%Aigaion2 BibTeX export from HES SO Valais Publications
%Saturday 02 May 2026 02:35:14 PM

@INPROCEEDINGS{,
    author = {Dinani, Mina Aghaei and Rizzo, Gianluca and holzer, Adrien and Nguyen, Hung and Marsan, Marco G Ajmone},
  keywords = {Distributed Learning, energy efficiency, Gossip Learning},
     month = may,
     title = {Context-Aware Orchestration of Energy-Efficient Gossip Learning Schemes},
   journal = {2024 IEEE World AI IoT Congress (AIIoT)},
      year = {2024},
       url = {https://ieeexplore.ieee.org/document/10578973},
       doi = {10.1109/AIIoT61789.2024.10578973},
  abstract = {Fully distributed learning schemes such as Gossip
Learning (GL) are gaining momentum due to their scalability and
effectiveness even in dynamic settings. However, they often imply
a high utilization of communication and computing resources,
whose energy footprint may jeopardize the learning process, particularly on battery-operated IoT devices. To address this issue,
we present Optimized Gossip Learning (OGL), a distributed
training approach based on the combination of GL with adaptive
optimization of the learning process, which allows for achieving
a target accuracy while minimizing the energy consumption of
the learning process. We propose a data-driven approach to
OGL management that relies on optimizing in real-time for each
node the number of training epochs and the choice of which
model to exchange with neighbors based on patterns of node
contacts, models’ quality, and available resources at each node.
Our approach employs a DNN model for dynamic tuning of the
aforementioned parameters, trained by an infrastructure-based
orchestrator function. We performed our assessments on two
different datasets, leveraging time-varying random graphs and
a measurement-based dynamic urban scenario. Results suggest
that our approach is highly efficient and effective in a broad
spectrum of network scenarios.}
}