Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models
Suhan Guo, Jiahong Deng, Mengjun Yi +2
Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive…
cs.LG2024
Explaining Model Overfitting in CNNs via GMM Clustering
Hui Dou, Xinyu Mu, Mengjun Yi +3
Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challeng…