Agapi Rissaki

Agapi Rissaki

PhD Candidate

I am a PhD Candidate in the DATA Lab of the Khoury College of Computer Sciences at Northeastern University, advised by Wolfgang Gatterbauer and co-advised by Miguel Fuentes-Cabrera. My thesis focuses on query-based explanations for machine learning on structured data. I recently completed a multi-year research internship at RelationalAI, where I developed GNN explainability methods for relational deep learning and multi-agent LLM systems for automated database schema-to-ontology translation. Prior to this, I spent a semester as a Visiting Graduate Student at UC Berkeley, as part of the Simons Institute program on Logic and Algorithms in Database Theory and AI. Before joining Northeastern, I received the Electrical and Computer Engineering diploma from the National Technical University of Athens, where I was a member of CoReLab, advised by Dimitris Fotakis.

Interests

  • Explainable AI
  • Relational Deep Learning
  • Graph Machine Learning
  • LLMs & Agents

Education

  • BSc & MSc in Electrical and Computer Engineering

    National Technical University of Athens (NTUA), Athens, Greece

Publications

(2026). Database Views as Explanations for Relational Deep Learning. Proceedings of the VLDB Endowment 19.
(2024). Towards Unbiased Exploration in Partial Label Learning. Journal of Machine Learning Research 25.
(2024). Reconstructing the Mid-Infrared Spectra of Galaxies Using UV to Submillimeter Photometry and Deep Generative Networks. Astronomy and Computing 47.
(2024). Towards Agentic Schema Refinement. NeurIPS – Table Representation Learning Workshop.
(2022). BiaScope: Visual Unfairness Diagnosis for Graph Embeddings. IEEE VIS – Visualization in Data Science Symposium (VDS).
(2020). Solving Inverse Problems for Spectral Energy Distributions with Deep Generative Networks. NeurIPS – Machine Learning and the Physical Sciences Workshop.