Workshop on Deep Learning for Knowledge Graphs

About

Over the past years there has been a rapid growth in the use and the importance of Knowledge Graphs (KGs) along with their application to many important tasks. KGs are large networks of real-world entities described in terms of their semantic types and their relationships to each other. On the other hand, Deep Learning methods have also become an important area of research, achieving some important breakthrough in various research fields, especially Natural Language Processing (NLP) and Image Recognition.

In order to pursue more advanced methodologies, it has become critical that the communities related to Deep Learning, Knowledge Graphs, and NLP join their forces in order to develop more effective algorithms and applications. This workshop, in the wake of other similar efforts at previous Semantic Web conferences such as ESWC2018 as DL4KGs and ISWC2018, ESWC2019, ESWC 2020, ISWC2021 aims to reinforce the relationships between these communities and foster inter-disciplinary research in the areas of KG, Deep Learning, and Natural Language Processing.

Topics of Interest

New approaches for combining Deep Learning and Knowledge Graphs

Methods for generating Knowledge Graph (node) embeddings
Scalability issues
Temporal Knowledge Graph Embeddings
Novel approaches

Applications of combining Deep Learning and Knowledge Graphs

Recommender Systems leveraging Knowledge Graphs
Link Prediction and completing KGs
Ontology Learning and Matching exploiting Knowledge Graph-Based Embeddings
Knowledge Graph-Based Sentiment Analysis
Natural Language Understanding/Machine Reading
Question Answering exploiting Knowledge Graphs and Deep Learning
Approximate query answering on knowledge graphs
Entity Linking
Trend Prediction based on Knowledge Graphs Embeddings
Domain Specific Knowledge Graphs (e.g., Scholarly, Biomedical, Musical)
Applying knowledge graph embeddings to real world scenarios.

Keynote Speaker

Luc de Raedt

Director of Leuven.AI, KU Leuven

Luc De Raedt is full professor at the Department of Computer Science, KU Leuven, and director of Leuven.AI, the newly founded KU Leuven Institute for AI. He is a guestprofessor at Örebro University in the Wallenberg AI, Autonomous Systems and Software Program. He received his PhD in Computer Science from KU Leuven (1991), and was full professor (C4) and Chair of Machine Learning at the Albert-Ludwigs-University Freiburg, Germany (1999-2006). His research interests are in Artificial Intelligence, Machine Learning and Data Mining, as well as their applications. He is well known for his contributions in the areas of learning and reasoning, in particular, for his work on probabilistic and inductive programming. He co-chaired important conferences such as ECMLPKDD 2001 and ICML 2005 (the European and International Conferences on Machine Learning), ECAI 2012 and will chair IJCAI in 2022 (the European and international AI conferences). He is on the editorial board of Artificial Intelligence, Machine Learning and the Journal of Machine Learning Research. He is a EurAI and AAAI fellow, an IJCAI Trustee and received and ERC Advanced Grant in 2015.

Title: From Probabilistic Logics to Neuro-Symbolic Artificial Intelligence
Abstract: A central challenge to contemporary AI is to integrate learning and reasoning. The integration of learning and reasoning has been studied for decades already in the fields of statistical relational artificial intelligence and probabilistic programming. StarAI has focussed on unifying logic and probability, the two key frameworks for reasoning, and has extended this probabilistic logics machine learning principles. I will argue that StarAI and Probabilistic Logics form an ideal basis for developing neuro-symbolic artificial intelligence techniques. Thus neuro-symbolic computation = StarAI + Neural Networks. Many parallels will be drawn between these two fields and will be illustrated using the Deep Probabilistic Logic Programming language DeepProbLog.

Workshop Program and Proceedings

Workshop Program. (Date: October 24, 2022. All times are in CET.)

10:00 - 10:10 Welcome & Opening

Session 1: 10:10 - 11:10

10:10 - 10:30 Towards A Question Answering System over Temporal Knowledge Graph Embedding Kristian Otte, Kristian Simoni Vestermark, Huan Li and Daniele Dell'Aglio. (paper, video)
Best paper!
10:30 - 10:50 Transformer-based Subject Entity Detection in Wikipedia Listings Nicolas Heist and Heiko Paulheim. (paper, video)
10:50 - 11:10 Improving Language Model Predictions via Prompts Enriched with Knowledge Graphs Ryan Brate, Minh-Hoang Dang, Fabian Hoppe, Yuan He, Albert Meroño-Peñuela and Vijay Sadashivaiah. (paper)

11:10 - 11:30 Coffee break

Session 2: 11:30 - 12:30

11:30 - 11:50 Knowledge Graph Embeddings for Link Prediction: Beware of Semantics! Nicolas Hubert, Pierre Monnin, Armelle Brun and Davy Monticolo. (paper, video)
11:50 - 12:10 Neuro-symbolic learning for dealing with sparsity in cultural heritage image archives: an empirical journey Agnese Chiatti and Enrico Daga. (paper, video)
12:10 - 12:30 Bilingual Question Answering over DBpedia Abstracts through Machine Translation and BERT Michalis Mountantonakis, Michalis Bastakis, Loukas Mertzanis and Yannis Tzitzikas. (paper, video)

12:30 - 13:30 LUNCH BREAK

Keynote: Luc de Raedt

Session 3: 14:10 - 14:50

14:10 - 14:30 A Closer Look at Sum-based Embeddings for Knowledge Graphs Containing Procedural Knowledge Richard Nordsieck, Michael Heider, Anton Hummel and Joerg Haehner. (paper, video)
14:30 - 14:50 Knowledge Graph Embeddings for Causal Relation Prediction Aamod Khatiwada, Sola Shirai, Kavitha Srinivas and Oktie Hassanzadeh. (paper, video)

14:50 - 15:10 COFFEE BREAK

Session 4: 15:10 - 16:10

15:10 - 15:30 Invited Talk: Stream Embedding for Accrescent Knowledge Graphs. Afshin Sadeghi. (abstract)
15:30 - 15:50 Multi-label Classification using BERT and Knowledge Graphs with a Limited Training Dataset Malick Ebiele, Lucy McKenna, Malika Bendechache and Rob Brennan. (paper, video)
15:50 - 16:10 CosmOntology: Creating an Ontology of the Cosmos [position paper] Vasilis Efthymiou. (paper, video)
16:10 - 16:20 Closing

Submission Details

Papers must comply with the CEUR-WStemplate
Papers are submitted in PDF format via the workshop’s Easychair submission pages

Submissions can fall in one of the following categories:

Full research papers (8-10 pages)
Short research papers (4-6 pages)
Position papers (2 pages)
Lightning talks (1 page abstract)

Accepted papers (after blind review of at least 3 experts) will be published by CEUR–WS.

At least one of the authors of the accepted papers must register for the workshop (pre-conference only option) to be included into the workshop proceedings.

Organizing Committee

Mehwish Alam

FIZ Karlsruhe - Leibniz Institute for Information Infrastructure, Germany

Davide Buscaldi

Labortoire d'Informatique Paris Nord (LIPN), Paris, France

Michael Cochez

Vrije University of Amsterdam, the Netherlands

Francesco Osborne

Knowledge Media Institute (KMi), The Open University, UK

Diego Reforgiato Recupero

University of Cagliari, Cagliari, Italy

Program Committee

Pierre Monnin Orange, Belfort, France
Andreea Iana, University of Mannheim, Germany
Genet Asefa Gesese, FIZ Karlsruhe – Leibniz-Institut für Informationsinfrastruktur, Germany
Yiyi Chen, FIZ Karlsruhe – Leibniz-Institut für Informationsinfrastruktur, Germany
Daniel Daza, Vrije Universiteit Amsterdam, the Netherlands
Danilo Dessi, University of Cagliari, Italy
Mehdi Ali, University of Bonn, Germany
Heiko Paulheim, University of Mannheim, Germany
Russa Biswas, FIZ Karlsruhe - Leibniz Institute for Information Infrastructure, Germany
Paul Groth, University of Amsterdam, the Netherlands
Longquan Jiang, University of Hamburg, Germany
Rima Tuerker, FIZ Karlsruhe - Leibniz Institute for Information Infrastructure, Germany
Ricardo Usbeck, Hamburg University, Germany
Gerard De Melo, University of Potsdam, Germany
Xi Yan, University of Hamburg, Germany