Geometric deep learning approach to knot theory
arXiv:2305.16808v11 citations
Originality Synthesis-oriented
AI Analysis
This work addresses knot theory problems for mathematicians and computational scientists, but appears incremental as it applies existing geometric deep learning methods to a new domain.
The paper tackled the problem of predicting knot invariants by introducing a geometric deep learning approach that maps knots to graphs and uses graph neural networks, achieving high generalization capabilities.
In this paper, we introduce a novel way to use geometric deep learning for knot data by constructing a functor that takes knots to graphs and using graph neural networks. We will attempt to predict several knot invariants with this approach. This approach demonstrates high generalization capabilities.