Postdoctoral researcher · ELLIS member
I am interested in graphs as powerful representations of real-world phenomena and in developing machine learning methods that leverage their structure to support scientific discovery. My research spans representation learning on graphs, complex query answering over incomplete knowledge, and the development and evaluation of methods that generalize across domains.
Currently I am a postdoctoral researcher at Eindhoven University of Technology (TU/e), working on knowledge graphs and multimodal foundation models for materials discovery within the SimuLingua Horizon Europe project.
I completed my PhD at Vrije Universiteit Amsterdam cum laude in 2024. Before joining TU/e, I held postdoctoral positions at Amsterdam UMC, working on knowledge graphs and rare disease research, and at VU Amsterdam in the Learning & Reasoning Group. In 2026, I was awarded an NWO Veni grant for my proposal: Predicting Plausible Interactions in Biomedical Knowledge Graphs.
Recent Highlights
- We are organizing a session on Learning on Graphs for Scientific Discovery at the ELLIS Unconference 2026 in Paris, in December 2026.
- We organized the workshop on Learning and Reasoning with Graphs at BNAIC 2026 in Maastricht.
- SCORE: Similarity-Constrained Reweighting for Complex Query Answering on Knowledge Graphs has been accepted at NeurIPS 2026, introducing a data-efficient way to add soft similarity constraints to arbitrary variables in complex graph queries.
- EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge has been accepted at NeurIPS 2026, providing a dataset for constructing and maintaining knowledge graphs as new evidence appears in text.
- I've been awarded an NWO Veni grant of EUR 320,000 for my proposal Predicting Plausible Interactions in Biomedical Knowledge Graphs.
- I received a COST Short-Term Scientific Mission grant for a research visit to the University of Stuttgart on foundation models for knowledge graphs.
Research themes
Learning representations of structured knowledge
How can machine learning capture the information in graph-structured data? I study graph representation learning, including methods that combine graph structure with text [7] and multimodal data of proteins and molecules [6], scale learning to large graphs [4], and compute and explain similarities between entities [2].
Complex reasoning with learned representations
How can we answer expressive queries over graphs when information is missing? I develop neural and neuro-symbolic query answering methods that use learned representations to reason over incomplete graphs [8, 5, 3] and incorporate user preferences through soft constraints [1].
Applications to scientific discovery
How can graph learning and reasoning help scientists interpret data and investigate new hypotheses? I apply these methods to multimodal biomedical knowledge graphs [6], the interpretation of rare disease omics predictions, and materials discovery through knowledge graphs and multimodal foundation models in SimuLingua.
Selected Publications
For a complete publication list, see Google Scholar.
*Indicates equal contribution.
Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Combining graph queries with preferences that are hard to express as logical constraints.
Daniel Daza, Alberto Bernardi, Luca Costabello, Christophe Gueret, Masoud Mansoury, Michael Cochez, Martijn Schut.
Explaining Graph Neural Networks for Node Similarity on Graphs
Explaining which graph structures contribute to learned node similarity.
Daniel Daza, Cuong Xuan Chu, Trung-Kien Tran, Daria Stepanova, Michael Cochez, Paul Groth.
Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation
Examining neural query answering through simpler, relaxed queries.
Yannick Brunink*, Daniel Daza*, Yunjie He, Michael Cochez.
GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks
Learning which parts of a graph to sample for scalable representation learning.
Taraneh Younesian, Daniel Daza, Emile van Krieken, Thiviyan Thanapalasingam, Peter Bloem.
UnRavL: A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs
Bringing learned predictions and symbolic structure together for graph pattern queries.
Tamara Cucumides, Daniel Daza, Pablo Barcelo, Michael Cochez, Floris Geerts, Juan L. Reutter, Miguel Romero Orth.
BioBLP: a modular framework for learning on multimodal biomedical knowledge graphs
Learning biomedical entity representations from graph structure and multiple data modalities.
Daniel Daza, D. Alivanistos, P. Mitra, T. Pijnenburg, M. Cochez, P. Groth.
Inductive Entity Representations from Text via Link Prediction
Connecting textual descriptions to representation learning on knowledge graphs.
Daniel Daza, M. Cochez, P. Groth.
Complex Query Answering with Neural Link Predictors
Answering complex logical queries by composing neural link predictions.
Erik Arakelyan*, Daniel Daza*, Pasquale Minervini*, Michael Cochez.