169 citations · 227 across the 13 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.LG2024
DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting
Yuxuan Shu, Vasileios Lampos
In multivariable time series (MTS) forecasting, existing state-of-the-art deep learning approaches tend to focus on autoregressive formulations and often overlook the potential of…
cs.CL2024
Unsupervised hard Negative Augmentation for contrastive learning
Yuxuan Shu, Vasileios Lampos
We present Unsupervised hard Negative Augmentation (UNA), a method that generates synthetic negative instances based on the term frequency-inverse document frequency (TF-IDF) retri…