Papers
Topics
Authors
Recent
2000 character limit reached

Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings (2403.09749v1)

Published 14 Mar 2024 in cs.LG and cs.AI

Abstract: In Time Series Classification (TSC), temporal pooling methods that consider sequential information have been proposed. However, we found that each temporal pooling has a distinct mechanism, and can perform better or worse depending on time series data. We term this fixed pooling mechanism a single perspective of temporal poolings. In this paper, we propose a novel temporal pooling method with diverse perspective learning: Selection over Multiple Temporal Poolings (SoM-TP). SoM-TP dynamically selects the optimal temporal pooling among multiple methods for each data by attention. The dynamic pooling selection is motivated by the ensemble concept of Multiple Choice Learning (MCL), which selects the best among multiple outputs. The pooling selection by SoM-TP's attention enables a non-iterative pooling ensemble within a single classifier. Additionally, we define a perspective loss and Diverse Perspective Learning Network (DPLN). The loss works as a regularizer to reflect all the pooling perspectives from DPLN. Our perspective analysis using Layer-wise Relevance Propagation (LRP) reveals the limitation of a single perspective and ultimately demonstrates diverse perspective learning of SoM-TP. We also show that SoM-TP outperforms CNN models based on other temporal poolings and state-of-the-art models in TSC with extensive UCR/UEA repositories.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Mind the Pool: Convolutional Neural Networks Can Overfit Input Size. In Proceedings of the 11th International Conference on Learning Representations (ICLR’23).
  2. On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. PLOS ONE, 10(7): 1–46.
  3. The UEA multivariate time series classification archive, 2018. arXiv:1811.00075.
  4. Time-Series Classification with COTE: The Collective of Transformation-Based Ensembles. IEEE Transactions on Knowledge and Data Engineering, 27(9): 2522–2535.
  5. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv:1803.01271.
  6. The UCI KDD archive of large data sets for data mining research and experimentation. ACM SIGKDD Explorations Newsletter, 2(2): 81–85.
  7. Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995.
  8. Soft-DTW: A Differentiable Loss Function for Time-Series. In Proceedings of the 34th International Conference on Machine Learning (ICML’17).
  9. The UCR time series archive. IEEE/CAA Journal of Automatica Sinica, 6(6): 1293–1305.
  10. ROCKET: Exceptionally Fast and Accurate Time Series Classification Using Random Convolutional Kernels. Data Mining and Knowledge Discovery, 34(5): 1454–1495.
  11. Time-Series Data Mining. ACM Comput. Surv., 45(1).
  12. Improving position encoding of transformers for multivariate time series classification. Data Mining and Knowledge Discovery, 38(1): 22–48.
  13. Temporal-attentive covariance pooling networks for video recognition. In Proceedings of the 35th Advances in Neural Information Processing Systems (NIPS’21).
  14. Pooling Methods in Deep Neural Networks, a Review. arXiv:2009.07485.
  15. Attentional pooling for action recognition. In Proceedings of the 31th Advances in Neural Information Processing Systems (NIPS’17).
  16. In Proceedings of the 26th Advances in Neural Information Processing Systems (NIPS’12).
  17. Matrix capsules with EM routing. In Proceedings of the 6th International Conference on Learning Representations (ICLR’18).
  18. Strip pooling: Rethinking spatial pooling for scene parsing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).
  19. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Proceedings of the 32nd International Conference on Machine Learning (ICML’15).
  20. Deep learning for time series classification: a review. Data Mining and Knowledge Discovery, 33(4): 917–963.
  21. InceptionTime: Finding AlexNet for Time Series Classification. Data Mining and Knowledge Discovery, 34(6): 1936–1962.
  22. ECG Heartbeat Classification: A Deep Transferable Representation. CoRR, abs/1805.00794.
  23. Multivariate LSTM-FCNs for time series classification. Neural Networks, 116: 237–245.
  24. Adam: A Method for Stochastic Optimization. In Proceedings of 3rd International Conference on Learning Representations (ICLR’15).
  25. Gradient-based learning applied to document recognition. In Proceedings of the IEEE.
  26. Learnable Dynamic Temporal Pooling for Time Series Classification. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI’21).
  27. Confident Multiple Choice Learning. In Proceedings of the 34th International Conference on Machine Learning (ICML’17).
  28. Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles. In Proceedings of the 30th Advances in Neural Information Processing Systems (NIPS’16).
  29. HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles for Time Series Classification. In Proceedings of the 16th IEEE International Conference on Data Mining (ICDM’16).
  30. DARTS: Differentiable Architecture Search. In Proceedings of the 7th International Conference on Learning Representations (ICLR’19).
  31. A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42: 11–24.
  32. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’15).
  33. Beyond temporal pooling: Recurrence and temporal convolutions for gesture recognition in video. International Journal of Computer Vision, 126: 430–439.
  34. Searching and mining trillions of time series subsequences under dynamic time warping. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’12).
  35. Spectral representations for convolutional neural networks. In Proceedings of the 28th Advances in Neural Information Processing Systems (NIPS’15).
  36. Dynamic routing between capsules. In Proceedings of the 31st Advances in Neural Information Processing Systems (NIPS’17).
  37. Schäfer, P. 2015. The BOSS is concerned with time series classification in the presence of noise. Data Mining and Knowledge Discovery, 29: 1505–1530.
  38. MultiRocket: multiple pooling operators and transformations for fast and effective time series classification. Data Mining and Knowledge Discovery, 36(5): 1623–1646.
  39. Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification. In Proceedings of the 9th International Conference on Learning Representations (ICLR’21).
  40. Attention is All you Need. In Proceedings of the 31st Advances in Neural Information Processing Systems (NIPS’17).
  41. Spatial–temporal pooling for action recognition in videos. Neurocomputing, 451: 265–278.
  42. Time series classification from scratch with deep neural networks: A strong baseline. In Proceedings of the International Joint Conference on Neural Networks (IJCNN’17).
  43. Dynamic Sparse Network for Time Series Classification: Learning What to “See”. In Proceedings of the 36th Advances in Neural Information Processing Systems (NIPS’22).
  44. Mixed Pooling for Convolutional Neural Networks. Rough Sets and Knowledge Technology, 364–375.
  45. A large margin time series nearest neighbour classification under locally weighted time warps. Knowledge and Information Systems, 59(1): 117–135.
  46. A Transformer-Based Framework for Multivariate Time Series Representation Learning. In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’21).
  47. Tapnet: Multivariate time series classification with attentional prototypical network. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI’20).
  48. T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification. In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI’22).
  49. Neural Architecture Search with Reinforcement Learning. In Proceedings of the 5th International Conference on Learning Representations (ICLR’17).

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free