SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning

arXiv:2609.32676 · cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Fine-Tuning — 47× in this paper · explained in 5 episodes
• Core — 29× in this paper · explained in 2 episodes
• Fidelity — 25× in this paper · explained in 2 episodes
• Foundation Model — 21× in this paper · explained in 3 episodes
• Foundation Models — 13× in this paper · explained in 7 episodes
• Time Series Forecasting — 12× in this paper · explained in 3 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Robustness — 10× in this paper · explained in 5 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Component-based Structural Fidelity Enhancement — 7× in this paper
• Consistency — 7× in this paper · explained in 3 episodes
• Semantic-Invariant Adversarial Augmentation — 7× in this paper
• Adaptation — 6× in this paper · explained in 1 episode
• Downstream Tasks — 6× in this paper · explained in 2 episodes
• Linear Probing — 4× in this paper · explained in 2 episodes
• Over-smoothing — 4× in this paper · explained in 4 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Generative AI — 2× in this paper · explained in 2 episodes
• Time Series Foundation Models (TSFMs) — 2× in this paper · explained in 2 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Mean Absolute Error — 1× in this paper
• Mean Squared Error — 1× in this paper
• Non-stationarity — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning (PEFT) — 1× in this paper · explained in 4 episodes
• Total Variation — 1× in this paper
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• UniTS: A Unified Multi-Task Time Series Model
• Adam: A Method for Stochastic Optimization
• CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling
• Prefix-Tuning: Optimizing Continuous Prompts for Generation
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
• Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
• Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
• AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

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