Abstract
Learning unbiased decision boundaries is crucial for time series classification. Real-world datasets typically exhibit long-tailed natures of class distributions, which results in an imbalanced feature space after training, i.e., decision boundaries will be easily biased towards dominant classes that dominate the feature space. However, existing methods mostly train models from artificially balanced datasets, making it still unclear how to deal with the long-tailed natures of time series data in real-world scenarios. Motivated by this question, we analyze the similarities and differences between long-tailed time series classification and general long-tailed recognition, and propose a Feature Space Rebalancing (FSR) strategy for time series classification, which works jointly from both representation and data perspectives. Specifically, from the representation perspective, we design Balanced Contrastive Learning (BCL), which avoids excessive intra-class compaction of tail classes by introducing a balanced supervised contrastive loss with hierarchical prototypes, resulting in a balanced feature space and better generalization. From the data perspective, we explore the effectiveness of traditional data augmentation on long-tailed distributions and propose an Adaptive Temporal Augmentation (ATA) to rebalance the potential feature space at the temporal level. Extensive experiments on multiple long-tailed time series datasets demonstrate its superiority, including different class distributions and imbalance ratios.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, L., Yao, L., Wang, X., Kanhere, S.S., Guo, B., Yu, Z.: Adversarial multi-view networks for activity recognition. Proc. ACM Interact. Mob. Wearable Ubiquit. Technol. 4, 1–22 (2020)
Barshan, B., Yüksek, M.C.: Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. Comput. J. 57, 1649–1667 (2014)
Cao, K., Wei, C., Gaidon, A., Aréchiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Proceedings of NeurIPS (2019)
Chen, H., Huang, C., Huang, Q., Zhang, Q., Wang, W.: ECGadv: generating adversarial electrocardiogram to misguide arrhythmia classification system. In: Proceedings of AAAI (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: Proceedings of ICML (2020)
Cui, Y., Jia, M., Lin, T., Song, Y., Belongie, S.J.: Class-balanced loss based on effective number of samples. In: Proceedings of CVPR (2019)
Dau, H.A., et al.: The UCR time series archive. IEEE CAA J. Autom. Sinica 6, 1293–1305 (2019)
Dempster, A., Schmidt, D.F., Webb, G.I.: MiniRocket: a very fast (almost) deterministic transform for time series classification. In: Proceedings of KDD (2021)
Deng, G., Han, C., Dreossi, T., Lee, C., Matteson, D.S.: IB-GAN: a unified approach for multivariate time series classification under class imbalance. In: Proceedings of SDM (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Huang, H., Xu, C., Yoo, S., Yan, W., Wang, T., Xue, F.: Imbalanced time series classification for flight data analyzing with nonlinear granger causality learning. In: Proceedings of CIKM (2020)
Jiang, Z., Chen, T., Chen, T., Wang, Z.: Improving contrastive learning on imbalanced data via open-world sampling. In: Proceedings of NeurIPS (2021)
Kang, B., Li, Y., Xie, S., Yuan, Z., Feng, J.: Exploring balanced feature spaces for representation learning. In: Proceedings of ICLR (2021)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: Proceedings of ICLR (2020)
Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: Proceedings of CVPR (2017)
Lee, D., Lee, S., Yu, H.: Learnable dynamic temporal pooling for time series classification. In: Proceedings of AAAI (2021)
Li, G., Choi, B., Xu, J., Bhowmick, S.S., Chun, K., Wong, G.L.: ShapeNet: a shapelet-neural network approach for multivariate time series classification. In: Proceedings of AAAI (2021)
Li, T., et al.: Targeted supervised contrastive learning for long-tailed recognition. In: Proceedings of CVPR (2022)
Lin, T., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of ICCV (2017)
Reiss, A., Stricker, D.: Introducing a new benchmarked dataset for activity monitoring. In: 16th International Symposium on Wearable Computers, ISWC 2012, Newcastle, United Kingdom, 18–22 June 2012 (2012)
Ren, J., et al.: Balanced meta-softmax for long-tailed visual recognition. In: Proceedings of NeurIPS (2020)
Wang, J., et al.: Seesaw loss for long-tailed instance segmentation. In: Proceedings of CVPR (2021)
Wang, P., Han, K., Wei, X., Zhang, L., Wang, L.: Contrastive learning based hybrid networks for long-tailed image classification. In: Proceedings of CVPR (2021)
Wen, Q., et al.: Time series data augmentation for deep learning: a survey. In: Proceedings of IJCAI (2021)
Yue, Z., et al.: TS2Vec: towards universal representation of time series. In: Proceedings of AAAI (2022)
Zang, Y., Huang, C., Loy, C.C.: FASA: feature augmentation and sampling adaptation for long-tailed instance segmentation. In: Proceedings of ICCV (2021)
Zha, D., Lai, K.H., Zhou, K., Hu, X.: Towards similarity-aware time-series classification. In: Proceedings of SDM (2022)
Zhang, Y., Kang, B., Hooi, B., Yan, S., Feng, J.: Deep long-tailed learning: a survey. CoRR (2021)
Zhao, P., et al.: T-SMOTE: temporal-oriented synthetic minority oversampling technique for imbalanced time series classification. In: Proceedings of IJCAI (2022)
Zhou, B., Cui, Q., Wei, X., Chen, Z.: BBN: bilateral-branch network with cumulative learning for long-tailed visual recognition. In: Proceedings of CVPR (2020)
Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of AAAI (2021)
Acknowledgements
This paper is partially supported by the National Natural Science Foundation of China (No. 62072427, No. 12227901), the Project of Stable Support for Youth Team in Basic Research Field, CAS (No. YSBR-005), Academic Leaders Cultivation Program, USTC.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, P., Wang, X., Wang, B., Zhang, Y., Bai, L., Wang, Y. (2023). Long-Tailed Time Series Classification via Feature Space Rebalancing. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13943. Springer, Cham. https://doi.org/10.1007/978-3-031-30637-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-30637-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30636-5
Online ISBN: 978-3-031-30637-2
eBook Packages: Computer ScienceComputer Science (R0)