Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?
Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representations by predicting target embeddings in latent space rather than reconstructing raw signals. Yet evidence on their benefits remains mixed, and most studies test only a si...
Yu-Tong Feng, Bo-Wen Liao, See-Kiong Ng et al.
· 0 citations