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

arXiv:2609.02203 · cs.LG, cs.AI · Submitted 2026-09-02 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-02

Updated: 2026-09-02

Comments: 11 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Recurrence Plot — 28× in this paper
• Representation Learning — 23× in this paper · explained in 2 episodes
• Transformer — 22× in this paper · explained in 2 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Decode — 12× in this paper · explained in 2 episodes
• Time Series Representation Learning — 12× in this paper
• Time Series Representation Transfer — 8× in this paper
• Attention Mechanism — 6× in this paper · explained in 3 episodes
• Time Series Model — 6× in this paper
• Embeddings — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Ablation study — 4× in this paper · explained in 1 episode
• Time Series Transformer — 4× in this paper
• Transfer Learning — 4× in this paper · explained in 10 episodes
• Cross-Attention Mechanism — 3× in this paper · explained in 2 episodes
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Affective Computing — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Predictive Coding — 1× in this paper · explained in 2 episodes
• Recover-At-The End — 1× in this paper
• Time Series Forecasting — 1× in this paper · explained in 3 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Data augmentation using synthetic data for time series classification with deep residual networks
• SOM-VAE: Interpretable Discrete Representation Learning on Time Series
• Unsupervised Scalable Representation Learning for Multivariate Time Series
• Similarity Preserving Representation Learning for Time Series Clustering
• Improving Clinical Predictions through Unsupervised Time Series Representation Learning
• TimeNet: Pre-trained deep recurrent neural network for time series classification
• Representation Learning with Contrastive Predictive Coding
• The UEA multivariate time series classification archive, 2018
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Time-Series Representation Learning via Temporal and Contextual Contrasting
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Decomposing Motion and Content for Natural Video Sequence Prediction
• CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks