Overview

Time series data is ubiquitous in finance, healthcare, and engineering. Our research develops principled deep learning methods tailored to the unique structure of sequential data.

Key Directions

Self-Attention for Time Series: We critically evaluate whether Transformer-based self-attention is truly beneficial for time series forecasting, challenging prevailing assumptions and proposing efficient alternatives (CATS, NeurIPS 2024).

Sharpness-Aware Training: We adapt sharpness-aware minimization (SAM) to exploit the periodic structure of time series, achieving faster convergence and better generalization in classification and forecasting tasks (Applied Soft Computing 2023).

Anomaly Detection: We combine differential privacy techniques with upsampling strategies to improve anomaly detection in highly imbalanced industrial datasets (Engineering Applications of AI 2026).

Diffusion-based Generation: We develop TimeBridge, a diffusion bridge model that uses learned priors for controllable and realistic time series generation (KDD 2026).

Representative Papers

Are Self-Attentions Effective for Time Series Forecasting? · NeurIPS 2024
Fast sharpness-aware training for periodic time series classification and forecasting · Applied Soft Computing 2023
Differentially private upsampling for enhanced anomaly detection in imbalanced data · Engineering Applications of AI 2026
← Back to Research