kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning

TL;DR

This paper introduces kHGCN, a curvature-aware hyperbolic graph neural network that better models heterogeneous tree-like structures by leveraging continuous and discrete curvature, leading to improved performance in node classification and link prediction.

Contribution

The paper proposes a novel curvature-aware hyperbolic GCN that encodes network topology through curvature, addressing heterogeneity in tree-like data for enhanced modeling.

Findings

kHGCN outperforms existing models in node classification.

kHGCN achieves superior results in link prediction.

Curvature-guided message passing improves long-range information propagation.

Abstract

The prevalence of tree-like structures, encompassing hierarchical structures and power law distributions, exists extensively in real-world applications, including recommendation systems, ecosystems, financial networks, social networks, etc. Recently, the exploitation of hyperbolic space for tree-likeness modeling has garnered considerable attention owing to its exponential growth volume. Compared to the flat Euclidean space, the curved hyperbolic space provides a more amenable and embeddable room, especially for datasets exhibiting implicit tree-like architectures. However, the intricate nature of real-world tree-like data presents a considerable challenge, as it frequently displays a heterogeneous composition of tree-like, flat, and circular regions. The direct embedding of such heterogeneous structures into a homogeneous embedding space (i.e., hyperbolic space) inevitably leads to heavy distortions. To mitigate the aforementioned shortage, this study endeavors to explore the curvature between discrete structure and continuous learning space, aiming at encoding the message conveyed by the network topology in the learning process, thereby improving tree-likeness modeling. To the end, a curvature-aware hyperbolic graph convolutional neural network, \{kappa}HGCN, is proposed, which utilizes the curvature to guide message passing and improve long-range propagation. Extensive experiments on node classification and link prediction tasks verify the superiority of the proposal as it consistently outperforms various competitive models by a large margin.