Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting

ArXi:2606.04833v1 Announce Type: cross Initially developed for natural language processing, Transformer architectures and attention mechanisms are now central to a wide range of deep learning models, including applications in time series forecasting. A standard attention mechanism, however, implicitly assumes homophilic interactions, limiting its ability to model data with positive and negative dependencies, such as time series. In this work, we