Distributed JEPA: A Self-Supervised Framework for Energy Forecasting
A distributed Joint Embedding Predictive Architecture for self-supervised learning from heterogeneous energy time-series that predicts latent representations of masked temporal segments while integrating temporal observations and contextual information within a shared embedding space to prevent representation collapse.
Liana Toderean, T. Cioara, Vasilis Michalakopoulos et al.
· 0 citations