activity
20242026
most citedDeep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

12 citations · 12 across the 5 of their papers we have counts for

collaborators
Showing 2024Show all

5 papers · 1 filter

cs.CV2024

Are Sparse Neural Networks Better Hard Sample Learners?

Qiao Xiao, Boqian Wu, Lu Yin +4

While deep learning has demonstrated impressive progress, it remains a daunting challenge to learn from hard samples as these samples are usually noisy and intricate. These hard sa…

cs.LG2024

LiMTR: Time Series Motion Prediction for Diverse Road Users through Multimodal Feature Integration

Camiel Oerlemans, Bram Grooten, Michiel Braat +3

Predicting the behavior of road users accurately is crucial to enable the safe operation of autonomous vehicles in urban or densely populated areas. Therefore, there has been a gro…

cs.LG2024

Unveiling the Power of Sparse Neural Networks for Feature Selection

Zahra Atashgahi, Tennison Liu, Mykola Pechenizkiy +3

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated p…

cs.CL2024

Dynamic Data Pruning for Automatic Speech Recognition

Qiao Xiao, Pingchuan Ma, Adriana Fernandez-Lopez +7

The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitivel…

cs.LG2024

Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers

Zahra Atashgahi, Mykola Pechenizkiy, Raymond Veldhuis +1

Efficient time series forecasting has become critical for real-world applications, particularly with deep neural networks (DNNs). Efficiency in DNNs can be achieved through sparse…