News
-
DiscoveryLab members attending and presenting work at NeurIPS2023!
Dimitrios Alivanistos, Daniel Daza, and Michael Cochez of the Discovery Lab attended NeurIPS2023 in New Orleans!
Excellent opportunity for inspiration, networking and promoting the work done at the Lab.
-
New journal publication: 'BioBLP: a modular framework for learning on multimodal biomedical knowledge graphs'
After almost a year of extensive research, BioBLP is published! We explore the combination of multimodal pretrained attribute encoders with Knowledge Graph Embeddings for biomedical Link Prediction!
Congrats to Daniel Daza, Dimitrios Alivanistos, Thom Pijnenburg, Payal Mitra, Michael Cochez and Paul Groth!
-
DiscoveryLab members hosting the local Amsterdam meet-up for Learning on Graphs 2023!
Thom Pijnenburg, Dimitrios Alivanistos, Daniel Daza, and Michael Cochez of the Discovery Lab alongside a team of colleagues from the VU university organized the local Amsterdam meet-up of the global Learning on Graphs conference LoGAMS!
It took place in the Elsevier headquarters in Radarweg and attracted researchers working on graphs and machine learning!
-
DiscoveryLab academic manager gave a keynote at the DL4LD workshop
Michael Cochez, academic lab manager of the discovery lab was invited to give a keynote at the 3rd Workshop DL4LD: Addressing Deep Learning, Relation Extraction, and Linguistic Data
-
DiscoveryLab members win the LM-KBC competition!
Dimitrios Alivanistos and Michael Cochez of the Discovery Lab alongside a team of colleagues from the university win the ISWC2022 LM-KBC competition!
-
Masoud Mansoury organizes MORS@RecSys2022
After a sucessful edition last year Masoud Mansoury, who is a researcher from the discovery lab, will organize the 2nd Workshop on Multi-Objective Recommender Systems at the RecSys conference. Check the homepage of the workshop MORS@RecSys2022 for more information.
-
The discovery lab at ICT.Open 2022!
At the ICT.Open 2022 event, we will be presenting our work on approximate query answerring. Many interesting quesitons can be formulated as graph queries. However, in some cases, the graph does not have all the information to answer them. In this line of work we use machine learning to still find the best answer.
We will also present a general overview of our work in the lab.
-
Paper accepted at ICLR2022!
For the second year straight, the Discovery Lab will be at ICLR! This time members of the lab will present StarQE: Query Answering on hyper-relational KG’s.
-
Knowledge Graphs Book published
In a broad collaboration with top researchers in the field, Michael Cochez, academic manager of the discovery lab worked towards a comprehensive book which covers many aspects of Knowledge Graphs The book is available from https://kgbook.org/ and in print from Morgan&Claypool
-
Best Task Paper Award at SemEval 2021 – 'MeasEval - Extracting Counts and Measurements and their Related Contexts'
Corey Harper et. al. won the best task paper award at SemEval 2021! See https://semeval.github.io/SemEval2021/awards for the conference organizer’s writeup on it, and https://aclanthology.org/2021.semeval-1.38.pdf for the paper itself.
-
Masoud Mansoury joins the Discovery Lab
We are happy to announce that starting Masoud Mansoury is joing the Discovery Lab from July 2021 onwards. He will be working on Reinforcement learning over structured multi-modal information & Bias in Recommendation
-
Filling in the blanks of knowledge graphs -- article on elsevier connect
After receiving an Outstanding Paper Award for our paper on “Complex Query Answering with Neural Link Predictors” at ICLR 2021, people got curious how we work together with Elsevier to get our innovations into their products.
In an Elsevier Connect article article by Alison Bert, lab members Daniel Daza and Michael Cochez, shed some light on the work done in the paper and how the synergy between the lab and Elsevier works from an academic perspective. Georgios Tsatsaronis and Anita de Waard, VP for Data Science and Research Content Operations and VP of Research Collaborations at Elsevier, respectively, elaborate on the company perspective.
Read the Elsevier connect article here https://www.elsevier.com/connect/filling-in-the-blanks-of-knowledge-graphs and the ICLR paper here https://openreview.net/pdf?id=Mos9F9kDwkz
-
Outstanding paper award at ICLR 2021: 'Complex Query Answering with Neural Link Predictors'
Our paper “Complex Query Answering with Neural Link Predictors” has received an Outstanding Paper Award.
Out of the 860 papers of the ICLR program, only 8 selected papers, that have been deemed of exceptional quality, have received this recognition! More information can be found in the official ICLR announcement. The actual paper can be found on openreview: https://openreview.net/pdf?id=Mos9F9kDwkz.
Congratulations Daniel Daza and Michael Cochez, and also to our collaborators in this work, from the UCL Center of Artificial Intelligence, Erik Arakelyan and Pasquale Minervini!
In this work, we show how to re-use models for 1-hop link prediction on knowledge graphs, to answer more complex queries involving larger sub-graphs. We improve upon previous methods that require orders of magnitude more training data.
The paper will be presented virtually on May 6 in the Outstanding Paper conference session 00:00 - 01:00 PDT, 03:00 - 04:00 EDT, 09:00 - 10:00 CET, 15:00 - 16:00 CST.
-
Invited paper at GKR 2020 (workshop at ECAI 2020) published 'Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification'
Several members of the lab got invited to write a contributions to the proceedings of the GKR2020 workshop. In this paper, we propose an additional metric to be used for the evaluation of approximate knowledge graph query answering. We also propose a graph embedding model based on axis-aligbned hyperrectangles that seems weel suited for this task.
The paper is availble as an open access publication from the proceedings published in the Lecture Notes Artificial Intelligence series.
-
Paper accepted to IEEE Access - DeepKneeExplainer: Explainable Knee Osteoarthritis Diagnosis From Radiographs and Magnetic Resonance Imaging
In collaboration with researcher from Fraunhofer, Germany and ZB MED—Information Centre for Life Sciences, Cologne, Germany, Michael Cochez from the discovery lab got a paper accepted in IEEE Access. In this paper, we show the result of exhaustive experimentation with explainable neural network techniques applied on radiographs and Magnetic Resonance Imaging (MRI).
The paper is published as open access here: https://ieeexplore.ieee.org/document/9363889
IEEE Access: M. R. Karim, J. Jiao, T. Döhmen, M. Cochez, O. Beyan, D. Rebholz-Schuhmann and S. Decker, “DeepKneeExplainer: Explainable Knee Osteoarthritis Diagnosis From Radiographs and Magnetic Resonance Imaging,” in IEEE Access, vol. 9, pp. 39757-39780, 2021, doi: 10.1109/ACCESS.2021.3062493.
-
ICAI Interview with Rinke Hoekstra: ‘Academics help seeing the big picture.’
Rinke Hoekstra, Lead Architect at Elsevier, is Industry Director of Discovery Lab. Rinke was interviewed by ICAI to talk about the collaboration with the University of Amsterdam and Vrije Universiteit Amsterdam: ‘Within Elsevier this is already seen as one of the most successful collaborations with academic partners.’
Read the interview at the ICAI website.
-
Paper accepted at The Web Conference: 'Inductive Entity Representations from Text via Link Prediction'
Our paper, “Inductive Entity Representations from Text via Link Prediction”, has been accepted at The Web Conference, 2021. With Daniel Daza, Michael Cochez and Paul Groth, we investigate how to learn representations of entities in a knowledge graph given their textual description. We then reuse these representations in tasks of entity classification and information retrieval, obtaining significant improvements over previously proposed methods.
A preprint of this work can be found here: https://arxiv.org/abs/2010.03496
-
Paper accepted at ICLR 2021: 'Complex Query Answering with Neural Link Predictors'
Our paper “Complex Query Answering with Neural Link Predictors” was accepted for oral presentation at ICLR 2021. It is the result of a collaboration with Erik Arakelyan and Pasquale Minervini from UCL. We show how to re-use models for 1-hop link prediction on knowledge graphs, to answer more complex queries involving larger sub-graphs. We improve upon previous methods that require orders of magnitude more training data.
The paper will be presented virtually in the first week of May.
-
Paper accepted at ICML 2020 GRL Workshop: 'Message Passing Query Embedding'
The paper, titled “Message Passing Query Embedding” was accepted at the ICML 2020 Workshop on Graph Representation and Learning. It is authored by two of our lab members: Daniel Daza and Michael Cochez. The paper proposes a novel architecture for graph embeddings of knowledge graph queries, with important advantages compared to previous works.
-
How AI and knowledge graphs can make your research easier
Data scientists are developing a knowledge graph with researchers in mind in Elsevier’s DiscoveryLab, collaborating with Vrije Universiteit and University of Amsterdam.
Read the article on Elsevier Connect.
