I am a postdoctoral researcher at the Learning and Reasoning Group at the Vrije Universiteit Amsterdam. My research explores how graphs can be used as expressive representations of real-world phenomena, and how learning algorithms can exploit these representations to make predictions, answer queries, and support discovery. I work on both foundational aspects, such as neural architectures and algorithms for representation learning on graphs, and their applications to problems including relational reasoning, hypothesis generation over scientific knowledge graphs, and predictive models for science and engineering.

Recent Highlights

  • In our new preprint, we present new methods for answering logical queries over knowledge graphs, that allow to incorporate "similarity constraints" that are hard to represent with first-order logic.
  • GRAPES 🍇 has been accepted in Transactions on Machine Learning Research! we propose a method for scaling GNNs to graphs with up to 2M nodes and 60M edges.
  • I have defended my PhD with distinction cum laude. My thesis is avalable at this link.
  • UnRavL has been accepted to the 2024 Learning on Graphs conference!

Selected Publications

For a full list of publications, see Google Scholar.

Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Daniel Daza, Alberto Bernardi, Luca Costabello, Christophe Gueret, Masoud Mansoury, Michael Cochez, Martijn Schut. (preprint, 2025).
[paper] [code]

GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks
Taraneh Younesian, Daniel Daza, Emile van Krieken, Thiviyan Thanapalasingam, Peter Bloem, in Transactions on Machine Learning Research (2025).
[paper] [code]

UnRavL: A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs
Tamara Cucumides, Daniel Daza, Pablo Barcelo, Michael Cochez, Floris Geerts, Juan L Reutter, Miguel Romero Orth, in Learning on Graphs Conference 2024.
[paper]

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
Erik Arakelyan, Pasquale Minervini, Daniel Daza, Michael Cochez, and Isabelle Augenstein, in NeurIPS 2024.
[arxiv] [code]

BioBLP: A Modular Framework for Learning on Multimodal Biomedical Knowledge Graphs
Daniel Daza, Dimitrios Alivanistos, Payal Mitra, Thom Pijnenburg, Michael Cochez, and Paul Groth, in Journal of Biomedical Semantics (2023).
[paper] [code]

Inductive Entity Representations from Text via Link Prediction
Daniel Daza, Michael Cochez, and Paul Groth, in The Web Conference 2021.
[arXiv] [code] [bibtex]

Last update: Jan 6 2026.