Title : Graph Neural Networks with Precomputed Features
Abstract :
Graph neural networks (GNNs) have recently emerged as one the most popular machine learning models for processing and analyzing graph-structured data. In this talk, we focus on a GNN model that precomputes node features using a bank of neighborhood aggregation graph operators arranged in parallel. These GNN models have the natural advantage of reduced training and inference time due to the precomputations but are also fundamentally different from popular GNN variants that update node features through a sequential neighborhood aggregation procedure during training. We provide theoretical conditions under which a generic GNN model with parallel neighborhood aggregations (PA-GNNs, in short) are provably as powerful as the well-known Weisfeiler-Lehman (WL) graph isomorphism test in discriminating non-isomorphic graphs. We then apply PA-GNN for drug repurposing. Specifically, we pose drug repurposing as a link prediction problem to efficiently screen a large database of approved drugs and predict the possible treatment for novel diseases, e.g., coronavirus disease.
Biography: Sundeep Prabhakar Chepuri received his M.Sc. degree (cum laude) in electrical engineering and Ph.D. degree (cum laude) from the Delft University of Technology, The Netherlands, in July 2011 and January 2016, respectively. He was a Postdoctoral researcher at the Delft University of Technology, The Netherlands, a visiting researcher at University of Minnesota, USA, and at Aalto University, Finland. He has held positions at Robert Bosch, India, during 2007- 2009, and Holst Centre/imec-nl, The Netherlands, during 2010-2011. Currently, he is an Assistant Professor at the Department of ECE at the Indian Institute of Science (IISc) in Bengaluru, India.
Dr. Chepuri was a recipient of the Best Student Paper Award at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) in 2015, Best Student Paper Award (as co-author) at ASILOMAR 2019, and the Pratiksha Trust Young Investigator award. He was an Associate Editor of the EURASIP Journal on Advances in Signal Processing. Currently, he is an elected member of the EURASIP Technical Area Committee (TAC) on Signal Processing for Multisensor Systems, IEEE SPS Sensor Array and Multichannel Technical Committee (SAM-TC), IEEE SPS Signal Processing Theory and Methods Technical Committee (SPTM-TC), and an Associate Editor of IEEE Signal Processing Letters. His general research interest lies in the field of mathematical signal processing, statistical inference, and machine learning applied to network sciences and wireless communications.
vCal
iCal