Representation Learning of Geometric Trees
This addresses the need for better representation learning in domains like neuron morphology and river geomorphology, offering a tailored solution for geometric trees.
The paper tackled the problem of representing geometric trees, which have tree-structured layouts and spatial constraints often overlooked by traditional graph methods, by introducing a self-supervised learning framework with a provably recoverable and invariant neural network, achieving validation on eight real-world datasets.
Geometric trees are characterized by their tree-structured layout and spatially constrained nodes and edges, which significantly impacts their topological attributes. This inherent hierarchical structure plays a crucial role in domains such as neuron morphology and river geomorphology, but traditional graph representation methods often overlook these specific characteristics of tree structures. To address this, we introduce a new representation learning framework tailored for geometric trees. It first features a unique message passing neural network, which is both provably geometrical structure-recoverable and rotation-translation invariant. To address the data label scarcity issue, our approach also includes two innovative training targets that reflect the hierarchical ordering and geometric structure of these geometric trees. This enables fully self-supervised learning without explicit labels. We validate our method's effectiveness on eight real-world datasets, demonstrating its capability to represent geometric trees.