2 citations · 2 across the 4 of their papers we have counts for
3 papers · 1 filter
Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
Muhammad Fetrat Qharabagh, Artur Back de Luca, George Giapitzakis +1
Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge. In this work, we prove exact l…
Applying Graph Explanation to Operator Fusion
Keith G. Mills, Muhammad Fetrat Qharabagh, Weichen Qiu +5
Layer fusion techniques are critical to improving the inference efficiency of deep neural networks (DNN) for deployment. Fusion aims to lower inference costs by reducing data trans…
Reparameterization through Spatial Gradient Scaling
Alexander Detkov, Mohammad Salameh, Muhammad Fetrat Qharabagh +4
Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. Howeve…