Feature and Subgraph based Graph Neural Network (GNN) Explanations

This project will develop a graph neural network model that generates a prediction (e.g. detects anomalies) together with a set of explanations as to what the model based its prediction on. The model applies to dynamic graphs (such as wireless communication networks), and the explanations generated are either based on the properties of the graph nodes (e.g. parameters of network cells, such as traffic or power consumption) or the connectivity structure of the node (e.g. the state of the neighboring cells). Such explanations are crucial in identifying the source of anomalous behavior in complex systems with time-varying components. The development of these tools will greatly enhance human understanding of neural network behavior and make these AI models more trustworthy and reliable.

Faculty Supervisor:

Guillaume Rabusseau

Student:

Partner:

Samsung Electronics Canada

Discipline:

Computer science

Sector:

Manufacturing

University:

Université de Montréal

Program: