Turing Interest Group on Knowledge Graphs.
Attendance to the event is open to everyone.
- When: November 29, 2024 (9:30-16:00 GMT)
- Where: Edinburgh Future Institute, University of Edinburgh
- Format: In-person (up to 60-participants).
- Recording: To be added
Registration, Sponsorship and Call for presentations and/or posters:
- Registration form here (in-person attendance)
- Travel grants: Around 10 travel grants of around £100 are available to support the participation of PhD students and early postdocs.
- To apply email the Interest Group organisers with the following information: (1) full name, (2) institution, (3) if you are a PhD or a postdoc and (4) title of your presentation/poster.
09:15-09:45 Registration, poster set up and coffee.
09:45-10:00 Welcome to the meet-up.
10:00-10:45 Keynote I: The Quest for Schemas in Graph Databases
Angela Bonifati, Lyon 1 University
10:45-11:45 Short Presentations from members (10min + 5 QA)
- Elhadj Benkhelifa, University of Staffordshire, UK / Westcliff University: The Knowledge Graph Alliance
- Nitisha Jain, King's College London: Towards Interpretable Embeddings: Aligning Representations with Semantic Aspects
- Seferin James, British Standards Institution: Hierarchical routing across graph facets
- Marco Mesiti, Università degli Studi di Milano: Construction and enhancement of an RNA-based knowledge graph for discovering new RNA drugs
11:45-12:45 Lunch, Networking and posters (1h)
12:45-13:30 Keynote II: A Knowledge Graph with Task Representations and Applications in the Design of General-Purpose Task Completion Agents
Emine Yilmaz, University College London
13:30:-14:15 Short Presentations from members (5min + 2 QA)
- Xiaoxue Shen, The Alan Turing Institute: A structured knowledge graph for digital twins for structural dynamic systems
- Lorenzo Loconte, The University of Edinburgh: How to Turn your Knowledge Graph Embeddings into Generative Models
- Nikolai Kazantsev, University of Cambridge: Knowledge Graphs that Design Demand-driven Collaborations
- Pavlos Vougiouklis, Huawei Technologies R&D UK: Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning
- Seyed Amir Hosseini Beghaeiraveri, The University of Edinburgh: ShEx-to-Datalog: Optimizing Validation, Subsetting, and Reasoning over RDF
14:15-15:15 Coffee Break and Poster session (1h)
15:15-15:45 Panel Session: take home notes from the ISWC Special Session on Harmonising Generative AI and Semantic Web Technologies
15:45-16:00 Closing and Group Photo
Presenter | Affiliation | Poster Title |
---|---|---|
Milan Markovic | University of Aberdeen | Farm Explorer: A Tool for Calculating Transparent Greenhouse Gas Emissions |
Sevinj Teymurova | City St George's, University of London | OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignment |
Terence Egbelo | University of Sheffield | Topological bias in knowledge graphs: lessons from the biomedical domain |
Laura Balbi | University of Lisbon | LET'S AGREE TO DISAGREE: Neuro-Symbolic AI for conflict-aware learning over Knowledge Graphs |
Susana Nunes | University of Lisbon | Knowledge Graph-based Explanations for Biomedical AI |
Pedro Giesteira Cotovio | University of Lisbon | Learning and Explaining Knowledge Graph Alignment |
Lucas Ferraz | University of Lisbon | Development of an Ontological Fuzzy-search API for Semantic Knowledge Extraction |
Ricardo Carvalho | University of Lisbon | Time and Knowledge Aware Clinical Graph Data Mining |
Marta Silva | University of Lisbon | Complex Multi-Ontology Alignment through Geometric Operations on Language Embeddings |
Lorenzo Loconte | The University of Edinburgh | How to Turn your Knowledge Graph Embeddings into Generative Models |
Zhili Shen, Chenxin Diao | Huawei Technologies R&D UK | Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning |
Zhongtian Sun | University of Oxford | Building infectious disease databases and knowledge graphs with large language models |
Marco Mesiti | Università degli Studi di Milano | Construction and enhancement of an RNA-based knowledge graph for discovering new RNA drugs |