Status: Former Member
Email Address: [email protected]
“Peru Bhardwaj is a Ph.D. student at Trinity College Dublin, working at the intersection of Adversarial Machine Learning, Explainable AI, Natural Language Processing, and Knowledge Representation and Reasoning. Her thesis investigates the robustness of graph representation learning algorithms by designing adversarial attacks that lead to unintended predictions from the learned models. The focus of her research is Knowledge Graph Embedding (KGE) models that enable machine learning on large-scale knowledge graphs through feature vector representations of entities and relations. These models are increasingly used in user-facing applications in high-stake domains like healthcare and finance where motivated malicious actors can try to misuse them. Furthermore, the predictions of KGE models are non-interpretable and black-box in nature. Through methods that lead to KGE models’ failure (i.e. adversarial attacks), Peru’s research aims to provide an understanding of the predictive behaviour of these models, as well as improve the utility of KGE models in user applications that require trustworthy predictions. Her research work is funded jointly by Accenture Labs and the ADAPT Centre.
Before starting her Ph.D., Peru obtained a BAI degree in Computer Engineering from Trinity College Dublin in 2017. During this study, she completed a summer internship at ADAPT in 2016 and her final-year undergraduate project in 2017. Her undergraduate research was in the areas of Data Mapping, Data Integration, and Data Visualization with a focus on Linked Data and Semantic Web technologies. “