About
I am a Machine Learning researcher at Accenture Labs, Dublin, where I explore novel ways of applying machine learning to graph-structured data. I am broadly interested in knowledge representation and reasoning for explainable AI. I have a PhD in Computer Science from the Swiss Federal Institute of Technology, Lausanne (EPFL), where I worked on representation learning for multi-relational data under the supervision of Pierre Vandergheynst.
Besides machine learning, I am also fascinated by understanding human cognitive processes such as memory, learning, problem-solving, abstraction, common-sense reasoning. To satiate my intellectual appetite and further enrich my exploration in Artificial Intelligence, I embarked on a journey into studying Cognitive Sciences at University College Dublin (UCD).
Interests
- Graph Representation Learning
- Knowledge Graph Reasoning
- Explainability
- Neuro-symbolic Learning
Education
-
PhD in Electrical-Electronics Eng., 2021
École Polytechnique Fédérale de Lausanne
-
MSc in Electrical-Electronics Eng., 2017
Middle East Technical University
-
BSc in Electrical-Electronics Eng., 2013
Middle East Technical University
Featured Publications
Propagation on Multi-relational Graphs for Node Regression
Multi-relational Propagation (MrP) suggests a propagation approach designed for CONTINUOUS labels, and how to complete them on multi-relational and directed graphs.
Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation
In this study, we address the incompleteness in the numerical node attributes of a knowledge graph. We propose the algorithm MrAP, Multi-Relational Attribute Propagation, which we formulate within a message passing scheme.
Mask Combination of Multi-layer Graphs for Global Structure Inference
The structure of the data very often depends on complex relationships of multiple types. In this study, our main research question is “Can we support the structure inference process with a priori relational information about the data domain?”