DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing
DAIF is proposed, a data adaptive intermediate fusion framework that combines random matrix theory and non-parametric dependence measures to learn fusion structure directly from data to demonstrate its versatility across diverse supervised learning tasks.
Sagnik Nandy, Samriddha Lahiry, Pragya Sur et al.
· 0 citations