A5009663355- Graph Theory and Algorithms
- Neural Networks and Applications
- Advanced Graph Neural Networks
- Cognitive Computing and Networks
- Bayesian Modeling and Causal Inference
- Data Quality and Management
Technical University of Munich
2024-2025
Ruhr University Bochum
2023-2024
Cardinality Estimation over Knowledge Graphs (KG) is crucial for query optimization, yet remains a challenging task due to the semi-structured nature and complex correlations of data in typical KGs. In this work, we propose GNCE, novel approach that leverages knowledge graph embeddings Graph Neural Networks (GNN) accurately predict cardinality conjunctive queries GNCE first creates semantically meaningful all entities KG, which are then used learn representation using GNN estimate query. We...
This chapter delves into the emerging field of neuro-symbolic query optimization for knowledge graphs (KGs), presenting a comprehensive exploration how neural and symbolic techniques can be integrated to enhance processing. Traditional optimizers in rely heavily on methods, utilizing dataset summaries, statistics, cost models select efficient execution plans. However, these approaches often suffer from misestimations inaccuracies, particularly when dealing with complex queries or large-scale...
Cardinality Estimation over Knowledge Graphs (KG) is crucial for query optimization, yet remains a challenging task due to the semi-structured nature and complex correlations of typical Graphs. In this work, we propose GNCE, novel approach that leverages knowledge graph embeddings Graph Neural Networks (GNN) accurately predict cardinality conjunctive queries. GNCE first creates semantically meaningful all entities in KG, which are then integrated into given query, processed by GNN estimate...