Past Event: Oden Institute Seminar

Dynamic graph representation learning using tensor algebra

Shashanka Ubaru, Senior research scientist, IBM Research and visiting researcher, Oden Institute, UT Austin.

Abstract

*** This seminar will be presented both live in POB 6.304 and via Zoom.***

In recent years, a variety of graph neural networks (GNNs) have been successfully applied for representation learning and prediction on graphs. In many of the real-world applications, the underlying graph changes over time, however, most of the existing GNNs are inadequate for handling such dynamic graphs. In this study, we explore a novel technique for learning embeddings of dynamic graphs using a tensor algebra framework. The tensor framework is based upon the notion of tensor-tensor product, an algebraic formalism to multiply tensors, which inherits mimetic matrix properties. We show that the proposed tensor formalism is a natural extension of popular graph convolutional network (GCN) to the dynamic graph setting. We present numerical experiments on real-world datasets to demonstrate the intrinsic advantages of the proposed tensorial architecture for prediction tasks on dynamic graphs. We also consider an application related to the COVID-19 pandemic and show how the tensor framework can be used for early infection detection and uncertainty quantification in testing from contact tracing data.

Biography

Shashanka Ubaru is a senior research scientist at IBM Research. He is also a visiting researcher at the Oden Institute, UT Austin. Shashanka received his PhD in Computer Science from University of Minnesota.  Shashanka's research interests are in Machine Learning, Numerical Linear and Tensor Algebra, and Quantum Algorithms. Shashanka is a recipient of the IBM Herman Goldstine postdoctoral fellowship and IEEE ICMLA best paper award.