Position: Topological Deep Learning is the New Frontier for Relational Learning
It identifies open problems and invites research in TDL, which could impact relational learning but is incremental as it builds on existing fields.
The paper argues that topological deep learning (TDL) is a promising new frontier for relational learning, aiming to complement existing methods like graph representation learning by incorporating topological concepts to address various machine learning settings.
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.