Abstract: Graph neural networks (GNNs) are specifically designed for graph-structured data and have gained significant attention. However, training GNN on large-scale graphs remains challenging due to ...

The Kennedy College of Science, Richard A. Miner School of Computer & Information Sciences, invites you to attend a doctoral dissertation proposal defense by Nidhi Vakil, titled: "Foundations for ...

AI is ultimately a story about selfhood—and the answer will not be found in the machine, but in what mindful awareness allows us to recognize when we see ourselves reflected there.

Abstract: Training graph neural networks (GNNs) on large graphs is challenging due to both the high memory and computational costs of end-to-end training and the scarcity of detailed node-level ...

This blog post is the second in our Neural Super Sampling (NSS) series. The post explores why we introduced NSS and explains its architecture, training, and inference components. In August 2025, we ...

STM-Graph is a Python framework for analyzing spatial-temporal urban data and doing predictions using Graph Neural Networks. It provides a complete end-to-end pipeline from raw event data to trained ...

The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acs.jcim.5c01525. Efficiency analysis of different normalization strategies ...

With the recent popularity of neural networks comes the need for efficient serving of inference workloads. A neural network inference workload can be represented as a computational graph with nodes as ...