Timezone: »
This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted Relational Pooling (RP), draws from the theory of finite partial exchangeability to provide a framework with maximal representation power for graphs. RP can work with existing graph representation models and, somewhat counterintuitively, can make them even more powerful than the original WL isomorphism test. Additionally, RP allows architectures like Recurrent Neural Networks and Convolutional Neural Networks to be used in a theoretically sound approach for graph classification. We demonstrate improved performance of RP-based graph representations over state-of-the-art methods on a number of tasks.
Author Information
Ryan Murphy (Purdue University)
I am a Ph.D. candidate at Purdue University working with Professors Bruno Ribeiro (Computer Science) and Vinayak Rao (Statistics and Computer Science) on machine learning methods for graphs (networks) and unordered sequences. Applications for this work include predicting molecular properties, diagnosing neurodegenerative disease, and anomaly detection.
Balasubramaniam Srinivasan (Purdue University)
Vinayak A Rao (Purdue University)
Bruno Ribeiro (Purdue University)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: Relational Pooling for Graph Representations »
Wed Jun 12th 11:30 -- 11:35 PM Room Room 102
More from the Same Authors
-
2018 Poster: Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy »
Jiasen Yang · Qiang Liu · Vinayak A Rao · Jennifer Neville -
2018 Oral: Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy »
Jiasen Yang · Qiang Liu · Vinayak A Rao · Jennifer Neville