Scholar
Costas Mavromatis
Google Scholar ID: uDHOG6oAAAAJ
Amazon
Citations & Impact
Citations
723
H-index
11
i10-index
11
Publications
18
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Selected Publications:
- - ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs, EMNLP 2022
- - Tempoqr: Temporal Question Reasoning Over Knowledge Graphs, AAAI 2022
- - Graph InfoClust: Maximizing Coarse-Grain Mutual Information in Graphs, PAKDD 2021
- Passed Oral/Written Preliminary Exams with the work “Graph InfoClust: Leveraging Cluster-Level Information for Unsupervised Graph Representation Learning”.
- Successfully defended MEng/BSc Thesis “Blockchain Design and Implementation for Decentralized Optimal Power Flow”.
Research Experience
- Worked as an Applied Scientist intern at Amazon Web Services (AWS) during the summers of 2021 and 2022. Engaged in projects related to question answering, text classification, and graph learning.
Education
- Currently a Ph.D. Candidate at the Computer Science Department of the University of Minnesota, advised by Prof. George Karypis. Previously obtained a 5-year Degree from the University of Thessaly, Greece, advised by Prof. Manolis Vavalis.
Background
- Research interests span across natural language processing and graph machine learning. Experienced with Large Language Models, Graph Neural Networks, and Knowledge Graphs. Goal is to design AI systems that are reliable, truthful, and accurate.
Miscellany
- Contact: mav*ro016 AT um*n DOT edu (delete all asterisks *)
Co-authors