Is Channel Independent strategy optimal for Time Series Forecasting? (2310.17658v4)
Abstract: There has been an emergence of various models for long-term time series forecasting. Recent studies have demonstrated that a single linear layer, using Channel Dependent (CD) or Channel Independent (CI) modeling, can even outperform a large number of sophisticated models. However, current research primarily considers CD and CI as two complementary yet mutually exclusive approaches, unable to harness these two extremes simultaneously. And it is also a challenging issue that both CD and CI are static strategies that cannot be determined to be optimal for a specific dataset without extensive experiments. In this paper, we reconsider whether the current CI strategy is the best solution for time series forecasting. First, we propose a simple yet effective strategy called CSC, which stands for $\mathbf{C}$hannel $\mathbf{S}$elf-$\mathbf{C}$lustering strategy, for linear models. Our Channel Self-Clustering (CSC) enhances CI strategy's performance improvements while reducing parameter size, for exmpale by over 10 times on electricity dataset, and significantly cutting training time. Second, we further propose Channel Rearrangement (CR), a method for deep models inspired by the self-clustering. CR attains competitive performance against baselines. Finally, we also discuss whether it is best to forecast the future values using the historical values of the same channel as inputs. We hope our findings and methods could inspire new solutions beyond CD/CI.
- Multivariate time series dataset for space weather data analytics. Scientific Data, 7, 2020. URL https://api.semanticscholar.org/CorpusID:220430983.
- An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. ArXiv, abs/1803.01271, 2018. URL https://api.semanticscholar.org/CorpusID:4747877.
- Freeway performance measurement system: Mining loop detector data. Transportation Research Record, 1748:102 – 96, 2001. URL https://api.semanticscholar.org/CorpusID:108891582.
- Mlinear: Rethink the linear model for time-series forecasting. ArXiv, abs/2305.04800, 2023. URL https://api.semanticscholar.org/CorpusID:258557949.
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks : the official journal of the International Neural Network Society, 107:3–11, 2017. URL https://api.semanticscholar.org/CorpusID:6940861.
- The capacity and robustness trade-off: Revisiting the channel independent strategy for multivariate time series forecasting. ArXiv, abs/2304.05206, 2023. URL https://api.semanticscholar.org/CorpusID:258060249.
- Towards efficient electricity forecasting in residential and commercial buildings: A novel hybrid cnn with a lstm-ae based framework. Sensors (Basel, Switzerland), 20, 2020. URL https://api.semanticscholar.org/CorpusID:212621952.
- Reversible instance normalization for accurate time-series forecasting against distribution shift. In International Conference on Learning Representations, 2022. URL https://api.semanticscholar.org/CorpusID:251647808.
- Revisiting long-term time series forecasting: An investigation on linear mapping. ArXiv, abs/2305.10721, 2023. URL https://api.semanticscholar.org/CorpusID:258762346.
- Segrnn: Segment recurrent neural network for long-term time series forecasting. arXiv preprint arXiv:2308.11200, 2023.
- Scinet: Time series modeling and forecasting with sample convolution and interaction. In Neural Information Processing Systems, 2021. URL https://api.semanticscholar.org/CorpusID:252873681.
- Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In International Conference on Learning Representations, 2022. URL https://api.semanticscholar.org/CorpusID:251649164.
- A time series is worth 64 words: Long-term forecasting with transformers. ArXiv, abs/2211.14730, 2022. URL https://api.semanticscholar.org/CorpusID:254044221.
- Swish: a self-gated activation function. arXiv: Neural and Evolutionary Computing, 2017. URL https://api.semanticscholar.org/CorpusID:196158220.
- Spatial-temporal identity: A simple yet effective baseline for multivariate time series forecasting. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022. URL https://api.semanticscholar.org/CorpusID:251467892.
- Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In Neural Information Processing Systems, 2021. URL https://api.semanticscholar.org/CorpusID:235623791.
- Are transformers effective for time series forecasting? In Proceedings of the AAAI conference on artificial intelligence, volume 37, pp. 11121–11128, 2023.
- Informer: Beyond efficient transformer for long sequence time-series forecasting. In AAAI Conference on Artificial Intelligence, 2020. URL https://api.semanticscholar.org/CorpusID:229156802.
- Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. ArXiv, abs/2201.12740, 2022. URL https://api.semanticscholar.org/CorpusID:246430171.