aiqbench analysis
This paper addresses the critical challenge of class-incremental continual learning for multivariate time series by integrating deep temporal embeddings with statistical features to mitigate forgetting. The proposed dual-stream pipeline demonstrates competitive accuracy and low forgetting rates across five benchmark datasets, offering a practical solution for systems that must adapt to new categories without retraining from scratch. For practitioners dealing with evolving time-series data, this approach provides a robust framework for balancing model adaptability with knowledge retention.
Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification
arXiv:2606.03292v1 Announce Type: cross Abstract: Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification model. This is known as class-incremental continual learning, and in the case of multivariate time-series, is further complicated by the temporal structure of the data. In this paper, we present a novel approach for performing class incremental continual learning for the classification of multivariate time series data based upon the construction of a dual-stream feature extraction pipeline (using both deep temporal embedding features generated via a pre-trained frozen foundation model and application of statistical features). Evaluated on five benchmark datasets, the proposed system achieves competitive average accuracy across all datasets while maintaining low forgetting rates across all experimental configurations.
Abstract:Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification model. This is known as class-incremental continual learning, and in the case of multivariate time-series, is further complicated by the temporal structure of the data. In this paper, we present a novel approach for performing class incremental continual learning for the classification of multivariate time series data based upon the construction of a dual-stream feature extraction pipeline (using both deep temporal embedding features generated via a pre-trained frozen foundation model and application of statistical features). Evaluated on five benchmark datasets, the proposed system achieves competitive average accuracy across all datasets while maintaining low forgetting rates across all experimental configurations.
Machine Learning (stat.ML); Machine Learning (cs.LG)
arXiv:2606.03292 [stat.ML]
(or arXiv:2606.03292v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2606.03292 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 219 words