I am a postdoctoral researcher at the Translational AI Laboratory, in the Amsterdam University Medical Center. My research focuses on the development and study of machine learning methods that use structured representations to understand the world and make predictions. This ranges from methods that help us build structured representations, such as methods for information extraction and knowledge graph construction from text, to those that exploit structured representations, such as methods for graph embedding, link prediction, and approximate query answering over knowledge graphs.

Recent Activity

• New preprint: with GRAPES 🍇 we propose a method for scaling GNNs to graphs with up to 2M nodes and 60M edges.
• Our paper, Adapting Neural Link Predictors for Data-Efficient Complex Query Answering has been accepted to NeurIPS 2024!
• We're presenting Harnessing the Web and Knowledge Graphs for Automated Impact Investing Scoring at the KDD 2023 Workshop on AI for Climate Sustainability.
• New preprint! With BioBLP we propose to learn embeddings in biomedical knowledge graphs by incorporating multimodal data of proteins, molecules, and diseases.
• I've started a research internship at the Bosch Center for Artificial Intelligence, where I will work on topics related to representation learning on graphs.
• Our paper, SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning has been presented at the ACL 2022 Workshop on Structured Prediction for NLP.
• I've presented Inductive Entity Representations from Text via Link Prediction at the Web Conference 2021.
• Our paper, Complex Query Answering with Neural Link Predictors, has received an Outsdanding Paper Award at ICLR 2021! (see announcement.)
• New blogpost on Normalizing Flows.
• I've written a report for my virtual attendance to AKBC 2020.
• Our paper, Message Passing Query Embedding, has been accepted at the ICML 2020 GRL+ Workshop!

Publications

GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks
Taraneh Younesian, Thiviyan Thanapalasingam, Emile van Krieken, Daniel Daza, Peter Bloem (preprint).
[arxiv] [code]

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]

Harnessing the Web and Knowledge Graphs for Automated Impact Investing Scoring
Qingzhi Hu, Daniel Daza, Laurens Swinkels, Kristina Ūsaitė, Robbert-Jan ‘t Hoen, and Paul Groth, in KDD 2023 Workshop on AI for Climate Sustainability.
[arxiv]

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

SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning
Daniel Daza, Michael Cochez, and Paul Groth, in ACL 2022 Workshop on Structured Prediction for NLP.
[paper] [code] [bibtex]

Complex Query Answering with Neural Link Predictors
Erik Arakelyan, Daniel Daza, Pasquale Minervini, and Michael Cochez, in ICLR 2021 (🏆 Outstanding Paper Award).
[arXiv] [code] [bibtex]

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

Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification
Ruud van Bakel, Teodor Aleksiev, Daniel Daza, Dimitrios Alivanistos, and Michael Cochez, in International Workshop on Graph Structures for Knowledge Representation and Reasoning, 2020.
[arXiv] [bibtex]

Message Passing Query Embedding
Daniel Daza and Michael Cochez, in ICLR 2020 Workshop on Graph Representation Learning and Beyond.
[arXiv] [code] [bibtex]

A Modular Framework for Unsupervised Graph Representation Learning
Daniel Daza, Master's Thesis (2019), supervisor: Thomas Kipf.
[pdf]

Last update: Feb 5 2024