pith. sign in

arxiv: 1909.12641 · v1 · pith:42ODKRNTnew · submitted 2019-09-27 · 💻 cs.LG · stat.ML

Active Federated Learning

classification 💻 cs.LG stat.ML
keywords clientclientsdatafederatedgradientslearningmodelactive
0
0 comments X
read the original abstract

Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading gradients uses the client's bandwidth, so minimizing these transmission costs is important. The data on each client is highly variable, so the benefit of training on different clients may differ dramatically. To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client to maximize efficiency. We propose a cheap, simple and intuitive sampling scheme which reduces the number of required training iterations by 20-70% while maintaining the same model accuracy, and which mimics well known resampling techniques under certain conditions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ADKO: Agentic Decentralized Knowledge Optimization

    cs.LG 2026-05 unverdicted novelty 6.0

    ADKO is a decentralized framework where agents share compact GP-derived tokens and LM insights to achieve collaborative Bayesian optimization with a decomposed regret bound that includes compression and approximation losses.

  2. VARS-FL: Validation-Aligned Client Selection for Non-IID Federated Learning in IoT Systems

    cs.LG 2026-05 unverdicted novelty 6.0

    VARS-FL builds client reputation from validation loss reduction signals and uses sliding-window averaging plus log-scaled participation to select clients, yielding up to 36% faster convergence to 80% accuracy on non-I...

  3. EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    EvoCSFL combines candidate generation, a multi-objective metric, surrogate approximation, and evolutionary search to optimize client subsets in federated learning, reporting faster convergence and lower energy on imag...