TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecasting

1 code implementation • 26 Oct 2022 • Hyunwook Lee, Chunggi Lee, Hongkyu Lim, Sungahn Ko

In this paper, we examine the definition of shape and distortions, which are crucial for shape-awareness in time-series forecasting, and provide a design rationale for the shape-aware loss function.

Dynamic Time Warping Time Series +1

Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting

1 code implementation • ICLR 2022 • Hyunwook Lee, Seungmin Jin, Hyeshin Chu, Hongkyu Lim, Sungahn Ko

To evaluate the validness of the new perspective, we design a novel traffic forecasting model, called Pattern-Matching Memory Networks (PM-MemNet), which learns to match input data to the representative patterns with a key-value memory structure.