This repository is the implementation of TPFL: Tsetlin-Personalized Federated Learning with Confidence Based Clustering
, a novel method that implements Tsetlin Machine (TM) algorithm in Personalized Federated Learning (PFL) context for the first time. TPFL is implemented under 5 experimental setups. Paper >>> https://www.arxiv.org/abs/2409.10392
TPFL_Experiments.ipynb
: TPFL ImplementationFLIS_Baseline.ipynb
: FLIS ImplementationFedAvg_FedProx_Baselines.ipynb
: FedAvg and FedProx ImplementationIFCA_Baseline.ipynb
: IFCA ImplementationModel_Size_Report.ipynb
: Model Communication Cost Implementation
Run TPFL_Experiments.ipynb
notebook. We ran the notebooks on Google Colab Pro.
To see the results, please go the TPFL Report
directory.