← Back to all news
arXiv AI By Fang He, Wang-chien Lee

SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework

Read the original on arXiv AI →

SMart is a new time series representation learning framework that combines a multi-phase recurrence plot recovery task with a source dataset selector. The recovery task uses three alternative modes to guide the encoder in capturing time series dynamics, while the selector chooses multiple suitable source datasets to augment the target dataset during pre‑training. Experiments demonstrate that SMart surpasses state‑of‑the‑art models, reducing mean absolute error by up to 19.5% in regression and increasing classification accuracy by up to 1.34%.

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 AI.

Related stories

arXiv Machine Learning
Sep 3

Compositional Spectral Prompts for LLM-based Online Time Series Forecasting

The paper introduces CoSPOT, an online time series forecasting framework that uses a frozen pre‑trained large language model (LLM) as the core forecaster. CoSPOT adapts to evolving data by applying compositional spectral prompts—frequency‑domain basis prompts weighted by their amplitudes—allowing the model to represent unseen patterns as new combinations of learned bases while updating few parameters. Experiments on real‑world datasets show CoSPOT’s effectiveness in extended online phases and cross‑dataset scenarios with significant distribution shifts.

By Seungyoon Choi, Hyunchul Kim, Jae-Gil Lee, Chanyoung Park
llms
More like this →
arXiv Machine Learning
Jun 19

Spectral Retrieval-Augmented Time-Series Forecasting

arXiv:2606. 19412v1 Announce Type: new Abstract: Time series forecasting leverages historical patterns to predict future values, but traditional methods face challenges when dealing with complex, non-stationary patterns that are difficult to memorize during training.

By Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen, Hung Le
ragbenchmarks
More like this →
arXiv AI
Jun 16

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

arXiv:2508. 05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient.

By Lars Graf, Thomas Ortner, Stanis{\l}aw Wo\'zniak, Angeliki Pantazi
llmsbenchmarks
More like this →
arXiv Machine Learning
Sep 10

PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting

arXiv:2601.20845v2 Announce Type: replace Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require do...

By Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz
llmsfine-tuningefficiencybenchmarks
More like this →
arXiv Machine Learning
Oct 19

RTSM: Adapting Recursive Models to Multivariate Time-Series Classification

The paper introduces the Recursive Time-Series Model (RTSM), a deep-learning architecture that uses a learned convolutional temporal tokenizer, a single-state weight‑tied refinement module, and a pooled classification readout to classify multivariate time‑series data. On the 30 UEA datasets, RTSM achieves a mean accuracy of 72.81% under validation‑based configuration, surpassing all 17 evaluated deep‑learning models and outperforming MambaSL by 1.60 percentage points. Ablation studies show that the proposed tokenizer and single‑state design outperform simpler convolutional embeddings and two‑state variants, and the full classifier reaches 86.10% mean accuracy compared to 84.79% for a tokenizer‑only classifier.

By Georg Tenzing, Anna Tegon, Luca Benini, Thorir Mar Ingolfsson
ragnlp
More like this →