DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting
This work addresses a key bottleneck in multivariate time series forecasting for applications like finance or sensor data, though it is incremental as it builds on existing transformer and graph-based methods.
The paper tackles the challenge of balancing channel-dependent and channel-independent strategies in multivariate time series forecasting by proposing DGCformer, which groups relevant variables using graph clustering and applies hybrid attention mechanisms, achieving superior performance on eight datasets.
Multivariate time series forecasting tasks are usually conducted in a channel-dependent (CD) way since it can incorporate more variable-relevant information. However, it may also involve a lot of irrelevant variables, and this even leads to worse performance than the channel-independent (CI) strategy. This paper combines the strengths of both strategies and proposes the Deep Graph Clustering Transformer (DGCformer) for multivariate time series forecasting. Specifically, it first groups these relevant variables by a graph convolutional network integrated with an autoencoder, and a former-latter masked self-attention mechanism is then considered with the CD strategy being applied to each group of variables while the CI one for different groups. Extensive experimental results on eight datasets demonstrate the superiority of our method against state-of-the-art models, and our code will be publicly available upon acceptance.