arXiv Machine Learning June 3, 2026 By Pablo Garc\'ia-Santaclara, Bruno Fern\'andez-Castro, Rebeca Pilar D\'iaz-Redondo

Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 10

Improving Multivariate Time Series Classification with Class-Wise Training and Model Aggregation

arXiv:2609.07493v1 Announce Type: new Abstract: In this paper, we propose a class-wise dimension (channel) selection framework for Multivariate Time Series Classification (MTSC). Rather than applying...

By Mouhamadou Mansour Lo, Gildas Morvan, Mathieu Rossi, Fabrice Morganti, David Mercier

safety

arXiv AI

Aug 13

Representation Finetuning for Continual Learning

arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.

By Haihua Luo, Xuming Ran, Tommi K\"arkk\"ainen, Huiyan Xue, Zhonghua Chen, Qi Xu, Fengyu Cong

fine-tuning benchmarks

arXiv Machine Learning

Jun 11

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

arXiv:2511. 09789v2 Announce Type: replace Abstract: Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics.

By Fulong Yao, Wanqing Zhao, Chao Zheng, Xiaofei Han

llms benchmarks

arXiv Machine Learning

Jul 22

In-Context Time Series Classification with Random Convolutional Features

arXiv:2607. 19234v1 Announce Type: new Abstract: Time series classification is central to domains like medical signal analysis, industrial monitoring, and sensor-based activity recognition, where class information manifests as localized shapes, specific frequencies, temporal shifts, or complex cross-channel interactions.

By Joscha C\"uppers, Jilles Vreeken

benchmarks

arXiv AI

Jul 21

TypiCore: A Hybrid Active Query Strategy for Class-Incremental Learning on Time Series

arXiv:2607. 17632v1 Announce Type: cross Abstract: Time series data play a pivotal role across numerous domains, including healthcare and manufacturing.

By Gabor Szucs, Samuel Jacsev, Marcell Nemeth, Davide Dalle Pezze, Gian Antonio Susto

benchmarks

arXiv AI

Jun 26

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

arXiv:2606. 27095v1 Announce Type: cross Abstract: Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task.

By Augustinas Ju\v{c}as, Yangchen Pan

computer-vision safety

One email a morning, machine-written

Related stories

Improving Multivariate Time Series Classification with Class-Wise Training and Model Aggregation

Representation Finetuning for Continual Learning

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

In-Context Time Series Classification with Random Convolutional Features

TypiCore: A Hybrid Active Query Strategy for Class-Incremental Learning on Time Series

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning