Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Time series forecasting is a critical and challenging problem in many real applications. Recently, Transformer-based models prevail in time series forecasting due to their advancement in long-range dependencies learning. Besides, some models introduce series decomposition to further unveil reliable yet plain temporal dependencies. Unfortunately, few models could handle complicated periodical patterns, such as multiple periods, variable periods, and phase shifts in real-world datasets. Meanwhile, the notorious quadratic complexity of dot-product attentions hampers long sequence modeling. To address these challenges, we design an innovative framework Quaternion Transformer (Quatformer), along with three major components: 1). learning-to-rotate attention (LRA) based on quaternions which introduces learnable period and phase information to depict intricate periodical patterns. 2). trend normalization to normalize the series representations in hidden layers of the model considering the slowly varying characteristic of trend. 3). decoupling LRA using global memory to achieve linear complexity without losing prediction accuracy. We evaluate our framework on multiple real-world time series datasets and observe an average 8.1% and up to 18.5% MSE improvement over the best state-of-the-art baseline.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Self-Attention with Relative Position Representations
Shaw, P., Uszkoreit, J., & Vaswani, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2074 · Cited by 2,505 · cited 1×
“To investigate the relative positional information in sequence, [4, 20] propose to encode the position difference into Transformers, namely relative positional encodings.”
BackgroundRoFormer: Enhanced transformer with rotary position embedding
Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., & Liu, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127063 · Cited by 1,957
RoFormer: Enhanced Transformer with Rotary Position Embedding
Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., & Liu, Y. (2021) · arXiv · doi:10.48550/arxiv.2104.09864 · Cited by 1,952 · cited 1×
“Recently, [22] introduces a rotary position encoding scheme which is the most related work compared to ours.”
MethodTransformers in Time Series: A Survey
Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., & Sun, L. (2023) · Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/759 · Cited by 1,260
Self-citation
Research works printed but not linked: 29
- Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016). · arXiv
- Shaojie Bai J. Zico Kolter and Vladlen Koltun. 2018. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv:1803.01271 · arXiv
- Robert B. Cleveland, William S. Cleveland, Jean E. McRae, and Irma Terpenning. 1990. STL: A seasonal-trend decomposition procedure based on loess. Journal of Official Statistics 6, 1 (1990), 3--73.
- Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V Le, and Ruslan Salakhutdinov. 2019. Transformer-xl: Attentive language models beyond a fixedlength context. arXiv preprint arXiv:1901.02860 (2019). · arXiv
- 10.1198/jasa.2011.tm09771 · DOI · Paper page
- 10.1145/3447548.3467430 · DOI · Paper page
- 10.1080/14786444808646046 · doi:10.1080/14786444808646046
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (11 1997), 1735--1780.
- Robin John Hyndman and George Athanasopoulos. 2018. Forecasting: Principles and Practice (2nd ed.). OTexts, Australia.
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. PMLR, 448--456.
- Sangeetha Abdu Jyothi, Carlo Curino, Ishai Menache, Shravan Matthur Narayanamurthy, Alexey Tumanov, Jonathan Yaniv, Ruslan Mavlyutov, Inigo Goiri, Subru Krishnan, Janardhan Kulkarni, et al. 2016. Morpheus: Towards Automated {SLOs} for Enterprise Clusters. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). 117--134.
- Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR).
- Nikita Kitaev, Lukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The Efficient Transformer. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020.
- Guokun Lai Wei-Cheng Chang Yiming Yang and Hanxiao Liu. 2018. Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks. arXiv:1703.07015 · DOI · Paper page
- Juho Lee, Yoonho Lee, Jungtaek Kim, Adam Kosiorek, Seungjin Choi, and Yee Whye Teh. 2019. Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks. In Proceedings of the 36th International Conference on Machine Learning. 3744--3753.
- Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, and Xifeng Yan. 2019. Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting. In Advances in Neural Information Processing Systems, Vol. 32.
- Xuezhe Ma, Xiang Kong, Sinong Wang, Chunting Zhou, Jonathan May, Hao Ma, and Luke Zettlemoyer. 2021. Luna: Linear Unified Nested Attention. arXiv preprint arXiv:2106.01540 (2021). · arXiv
- Boris N Oreshkin, Dmitri Carpov, Nicolas Chapados, and Yoshua Bengio. 2019. NBEATS: Neural basis expansion analysis for interpretable time series forecasting. In Proceedings of the International Conference on Learning Representations (ICLR).
- 10.1016/j.ijforecast.2019.07.001 · DOI · Paper page
- 10.1016/j.ijforecast.2019.03.017 · DOI · Paper page
- Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. arXiv:1409.3215 · arXiv
- 10.1080/00031305.2017.1380080 · DOI · Paper page
- Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.
- 10.1145/3448016.3452779 · DOI
- 10.1145/3394486.3403271 · DOI
- Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS). 101--112.
- 10.1145/3366423.3380288 · DOI
- Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and Wancai Zhang. 2021. Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. In The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), Vol. 35. 11106--11115.
- 10.1109/TPWRS.2022.3175252 · DOI
Cited by
Long sequence time-series forecasting with deep learning: A survey
Chen, Z., Ma, M., Li, T., Wang, H., & Li, C. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101819 · Cited by 349
Transformers in Time-Series Analysis: A Tutorial
Ahmed, S., Nielsen, I. E., Tripathi, A., Siddiqui, S., Ramachandran, R. P., & Rasool, G. (2023) · Circuits, Systems, and Signal Processing · doi:10.1007/s00034-023-02454-8 · Cited by 305
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
Self-citationDiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models
Wen, H., Lin, Y., Xia, Y., Wan, H., Wen, Q., Zimmermann, R., & Liang, Y. (2023) · Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems · doi:10.1145/3589132.3625614 · Cited by 130
“The first is deterministic methods, including transformer-based approaches [5, 43, 52, 54] and RNNbased models [3].”
MethodSelf-citationUniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
Liu, X., Hu, J., Li, Y., Diao, S., Liang, Y., Hooi, B., & Zimmermann, R. (2024) · Proceedings of the ACM Web Conference 2024 · doi:10.1145/3589334.3645434 · Cited by 115
Metadata
- Authors
- Chen, W., Wang, W., Peng, B., Wen, Q., Zhou, T., & Sun, L.
- Venue
- Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2022-08-14
- Pages
- 146-156
- OpenAlex
- W4290945834
- Cited by
- 69
- References
- 4
- FWCI
- 11.18
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting. https://app.cochat.ai/papers/10.1145/3534678.3539234
- The paper
- Chen, W., Wang, W., Peng, B., Wen, Q., Zhou, T., & Sun, L. (2022). Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/3534678.3539234
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.