GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention. (arXiv:2104.05914v3 [cs.LG] UPDATED)

Forecasting graph-based time-dependent data has many practical applications.
This task is challenging as models need not only to capture spatial dependency
and temporal dependency within the data, but also to leverage useful auxiliary
information for accurate predictions. In this paper, we analyze limitations of
state-of-the-art models on dealing with temporal dependency. To address this
limitation, we propose GSA-Forecaster, a new deep learning model for
forecasting graph-based time-dependent data. GSA-Forecaster leverages graph
sequence attention (GSA), a new attention mechanism proposed in …

arxiv attention data forecasting graph graph-based time