Not stated in source
2025 Needs review
On the uniform expressivity of graph neural networks
Abstract
The main subject of this work are certain parameterized algorithms, known as Graph Neural Networks, which operate on graphs. Specifically, we analyze what functions on graphs these algorithms can compute, or in other words, we analyze their expressivity.
Keywords
Not available
Specialisations
Similar theses
- The expressivity and explainability of graph neural networks Matthew Morris · University of Oxford · 2026
- Spiking graph neural networks: A survey Sathvik Murli · Rutgers University · 2026
- Recommender Systems Enhanced by Graph Neural Networks Filip Stupka · 2026
- Graph Neural Networks for Writer Identification and Retrieval Oliver Pilizar · TU Wien · 2026
- On the Adversarial Robustness of Graph Neural Networks Sofiane Ennadir · Dalarna University Library · 2026
- One-Class Learning for Graph Neural Networks Marcos Paulo Silva Gôlo · Universidade de São Paulo · 2026
