Filters

Settings

Now showing1 - 2 of 2
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Towards WebAssembly-based federated learning
    (Springer, 2025-02)
    Gottschalk, Felix
    ;
    Schulte, Stefan
    ;
    Manikku Badu, Nisal Hemadasa
    ;
    Ebrahimi, Elmira
    ;
    Edinger, Janick
    WebAssembly is a portable binary instruction format designed to serve as a compilation target for high-level languages. While originally developed to run performance-intensive applications directly in Web browsers, WebAssembly supports these days a number of different hardware platforms across the compute continuum. This makes it a promising option to run services for training and inference in Federated Learning. To the best of our knowledge, there have been only a few practical approaches to realize Federated Learning using WebAssembly. Therefore, in this paper, we present a framework to achieve this. Our prototypical implementation shows that WebAssembly-based Federated Learning applications are highly portable while providing acceptable runtime overhead during model training.
    Publicationtype: Conference Paper
      36
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Adaption via selection: on client selection to counter concept drift in federated learning
    (Springer, 2025-02)
    Thomas, Julius
    ;
    Saile, Finn
    ;
    Fischer, Mathias
    ;
    Kaaser, Dominik
    ;
    Schulte, Stefan
    Federated Learning is a Machine Learning paradigm in which multiple devices jointly train a shared model without the need to share their local data. Most Federated Learning approaches assume that the data remains static. However, this assumption is unrealistic in real-world scenarios where data may change over time. In this paper we study the impact of concept drift on Federated Learning models with heterogeneous data distribution. Client selection directly impacts the model’s performance, and we observe that the local loss of clients under concept drift deviates. Nevertheless, most applications select clients randomly for each training round. Our main contribution therefore is a probabilistic client selection algorithm that introduces a bias towards clients with higher local loss in order to counter concept drift. Extensive evaluations show that our algorithm recovers a drop in accuracy incurred by concept drift up to five times faster than random sampling while retaining competitive performance.
    Publicationtype: Conference Paper
      73