This repository contains the code for a forecasting framework with vertical federated learning. The methods cover a linear autoregressive forecaster, SARIMAX, and an autoregressive tree-based forecaster: https://github.com/JoaquinAmatRodrigo/skforecast
- Secret-shared matrix operations and communication experiments:
ssmatrix.py
- Forecasting tests:
forecast_<DATASET>.py
- Secret-sharing primitives:
SSCalculation.py
andSSCalculate_Alternate.py
- VFL XGBoost code based on MP-FedXGB:
VerticalXGBoost.py
, with documentation: https://github.com/HikariX/MP-FedXGB - Original diffusion model for time series repository: https://github.com/AI4HealthUOL/SSSD. Additional results and minor extensions in: https://anonymous.4open.science/r/SSSD-DE14/README.md
- Rossman Sales: https://www.kaggle.com/c/rossmann-store-sales/data
- Air Quality: https://archive.ics.uci.edu/dataset/360/air+quality
- Flight Passengers: https://www.kaggle.com/datasets/chirag19/air-passengers
- SML 2010: https://archive.ics.uci.edu/dataset/274/sml2010
- PV Power: https://www.kaggle.com/datasets/anikannal/solar-power-generation-data