From Similarity to Superiority: Channel Clustering for Time Series Forecasting

arXiv:2404.01340v1 Announce Type: new
Abstract: Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that …

abstract arxiv attention channels clustering cs.ai cs.lg forecasting independent instances interactions leads performance series strategy studies time series time series forecasting type