Decentralized learning with budgeted network load using Gaussian copulas and classifier ensembles
This work addresses efficient model aggregation in decentralized networks for classification tasks, but it appears incremental as it builds on existing ensemble and copula methods.
The paper tackles the problem of decentralized learning where multiple learners with different datasets share models only once to limit network load, by introducing DELCO, a method that aggregates classifier predictions using Gaussian copulas, achieving competitive accuracy and increased robustness against dependent classifiers.
We examine a network of learners which address the same classification task but must learn from different data sets. The learners cannot share data but instead share their models. Models are shared only one time so as to preserve the network load. We introduce DELCO (standing for Decentralized Ensemble Learning with COpulas), a new approach allowing to aggregate the predictions of the classifiers trained by each learner. The proposed method aggregates the base classifiers using a probabilistic model relying on Gaussian copulas. Experiments on logistic regressor ensembles demonstrate competing accuracy and increased robustness in case of dependent classifiers. A companion python implementation can be downloaded at https://github.com/john-klein/DELCO