Cover Image

Soft-MSM: Differentiable Context-Aware Elastic Alignment for Time Series

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Holder, Christopher, Bagnall, Anthony
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rock the KASBA: Blazingly Fast and Accurate Time Series Clustering
by: Holder, Christopher, et al.
Published: (2024)

A Review and Evaluation of Elastic Distance Functions for Time Series Clustering
by: Holder, Chris, et al.
Published: (2022)

On time series clustering with k-means
by: Holder, Christopher, et al.
Published: (2024)

The FreshPRINCE: A Simple Transformation Based Pipeline Time Series Classifier
by: Middlehurst, Matthew, et al.
Published: (2022)

The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification
by: Middlehurst, Matthew, et al.
Published: (2026)

From BOP to BOSS and Beyond: Time Series Classification with Dictionary Based Classifiers
by: Large, James, et al.
Published: (2018)

Unsupervised Feature Based Algorithms for Time Series Extrinsic Regression
by: Guijo-Rubio, David, et al.
Published: (2023)

Convolutional and Deep Learning based techniques for Time Series Ordinal Classification
by: Ayllón-Gavilán, Rafael, et al.
Published: (2023)

Bake off redux: a review and experimental evaluation of recent time series classification algorithms
by: Middlehurst, Matthew, et al.
Published: (2023)

Soft Bayesian Context Tree Models for Real-Valued Time Series
by: Saito, Shota, et al.
Published: (2026)

Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens
by: Namazi, Alireza, et al.
Published: (2025)

On Efficient Real-Time Semantic Segmentation: A Survey
by: Holder, Christopher J., et al.
Published: (2022)

Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series
by: Hu, Yuxiao, et al.
Published: (2025)

aeon: a Python toolkit for learning from time series
by: Middlehurst, Matthew, et al.
Published: (2024)

SoftED: Metrics for Soft Evaluation of Time Series Event Detection
by: Salles, Rebecca, et al.
Published: (2023)

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
by: Hu, Yifan, et al.
Published: (2025)

Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting
by: Hong, Xiaobin, et al.
Published: (2025)

Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting
by: Yao, Yueyang, et al.
Published: (2025)

Soft Contrastive Learning for Time Series
by: Lee, Seunghan, et al.
Published: (2023)

CGSTA: Cross-Scale Graph Contrast with Stability-Aware Alignment for Multivariate Time-Series Anomaly Detection
by: Qi, Zhongpeng, et al.
Published: (2026)

Identifying Elasticities in Autocorrelated Time Series Using Causal Graphs
by: Tiedemann, Silvana, et al.
Published: (2024)

HIVE-COTE 2.0: a new meta ensemble for time series classification
by: Middlehurst, Matthew, et al.
Published: (2021)

Learning Soft Sparse Shapes for Efficient Time-Series Classification
by: Liu, Zhen, et al.
Published: (2025)

Differential Machine Learning for Time Series Prediction
by: Yadav, Akash, et al.
Published: (2025)

ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
by: Zhang, Jiawen, et al.
Published: (2024)

Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
by: Yang, Haonan, et al.
Published: (2026)

One-Time Soft Alignment Enables Resilient Learning without Weight Transport
by: Cheon, Jeonghwan, et al.
Published: (2025)

Towards Long-Context Time Series Foundation Models
by: Żukowska, Nina, et al.
Published: (2024)

Interpretability in Deep Time Series Models Demands Semantic Alignment
by: De Felice, Giovanni, et al.
Published: (2026)

FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation
by: Bai, Jun, et al.
Published: (2026)

Universal Time Series Generation with Neural Controlled Differential Equations
by: Berndt, Torben, et al.
Published: (2026)

Learning Interpretable Differentiable Logic Networks for Time-Series Classification
by: Yue, Chang, et al.
Published: (2025)

Modeling Time Series Dynamics with Fourier Ordinary Differential Equations
by: Guo, Muhao, et al.
Published: (2025)

TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
by: Chen, Jialin, et al.
Published: (2025)

Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning
by: Liang, Chen, et al.
Published: (2023)

Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting
by: Zhou, Ziyu, et al.
Published: (2025)

Universal Redundancies in Time Series Foundation Models
by: Bao, Anthony, et al.
Published: (2026)

Fuzzy Cluster-Aware Contrastive Clustering for Time Series
by: Wang, Congyu, et al.
Published: (2025)

Task-Aware Mixture-of-Experts for Time Series Analysis
by: Wu, Xingjian, et al.
Published: (2025)

Graph-Aware Contrasting for Multivariate Time-Series Classification
by: Wang, Yucheng, et al.
Published: (2023)