Jiliang Tang awarded an NSF grant

Jiliang Tang, Assistant Professors of Computer Science and Engineering, has been awarded an NSF grant entitled " New Frontiers of Graph Neural Networks: Scalability, Interpretability, Vulnerability and Stability".

 

Abstract

As new generalizations of traditional deep neural networks to graph-structured data, Graph Neural Networks (or GNNs) have demonstrated the power in the graph representation learning and have permeated numerous areas of science and technology. However, GNNs also inherited drawbacks of traditional deep neural networks including lack of interpretability and vulnerable and unstable to adversarial attacks. Moreover, the complexity of graph data introduces the scalability as a new limitation for GNNs -- examples of graph-structured data are not independent and the expansion of the neighborhood for even a single node by GNNs can rapidly involve a large portion of the graph or even the whole graph. These drawbacks have raised tremendous concerns to adopt GNNs in many critical applications pertaining to fairness, privacy, and safety. Though there are very recent efforts on the research of GNNs in terms of scalability, interpretability and vulnerability and building stable GNN models (or stability) , these studies are still at the  stage of initial development and a comprehensive investigation of these new frontiers of GNNs is critically desired. This project aims to tackle the major drawbacks of GNNs and greatly enlarge their usability in critical applications. To achieve the research goal, we systematically investigate the primary directions of GNNs including advanced principles for scalable GNNs, new mechanisms to interpret GNNs, and ingenious strategies to attack and secure GNNs. Each direction will dramatically extend the frontier through not only studying original problems, but also developing innovative solutions.