Graph-patchformer: Patch interaction transformer with adaptive graph learning for multivariate time series forecasting
Abstract: Highlights•Proposing structural encodings to improve the predictor’s performance.•Designing Patch Interaction Block (NIB) to promote broad interactions among patches.•Experiments on twelve benchmarks demonstrate the effectiveness of the proposed method.
External IDs:dblp:journals/nn/HouYJZSY26
Loading