1 code implementation • 31 May 2024 • Aditya Shankar, Lydia Y. Chen, Jérémie Decouchant, Dimitra Gkorou, Rihan Hai
We address those challenges and propose 'Secret-shared Time Series Forecasting with VFL' (STV), a novel framework that exhibits the following key features: i) a privacy-preserving algorithm for forecasting with SARIMAX and autoregressive trees on vertically partitioned data; ii) serverless forecasting using secret sharing and multi-party computation; iii) novel N-party algorithms for matrix multiplication and inverse operations for direct parameter optimization, giving strong convergence with minimal hyperparameter tuning complexity.
2 code implementations • 5 Apr 2024 • Ziyu Li, Hilco van der Wilk, Danning Zhan, Megha Khosla, Alessandro Bozzon, Rihan Hai
Pre-trained deep learning (DL) models are increasingly accessible in public repositories, i. e., model zoos.
no code implementations • 4 Apr 2024 • Aditya Shankar, Hans Brouwer, Rihan Hai, Lydia Chen
We introduce SiloFuse, a novel generative framework for high-quality synthesis from cross-silo tabular data.
no code implementations • 19 Jul 2022 • Ziyu Li, Rihan Hai, Alessandro Bozzon, Asterios Katsifodimos
Machine learning (ML) practitioners and organizations are building model zoos of pre-trained models, containing metadata describing properties of the ML models and datasets that are useful for reporting, auditing, reproducibility, and interpretability purposes.