Random Walk Guided Hyperbolic Graph Distillation
This work addresses the challenge of extracting task-specific and dynamic information from large-scale networks for downstream applications, representing a novel method for a known bottleneck in graph distillation.
The paper tackles the problem of graph distillation in Euclidean space struggling to capture tree-like geometry and dynamic properties of real-world networks, resulting in HyDRO, which outperforms state-of-the-art methods in node classification and link prediction tasks while preserving random walk properties for continual graph learning.
Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to generate condensed graphs, struggle to capture the inherent tree-like geometry of real-world networks, resulting in distilled graphs with limited task-specific information for downstream tasks. Furthermore, these methods often fail to extract dynamic properties from graphs, which are crucial for understanding information flow and facilitating graph continual learning. This paper presents the Hyperbolic Graph Distillation with Random Walks Optimization (HyDRO), a novel graph distillation approach that leverages hyperbolic embeddings to capture complex geometric patterns and optimize the spectral gap in hyperbolic space. Experiments show that HyDRO demonstrates strong task generalization, consistently outperforming state-of-the-art methods in both node classification and link prediction tasks. HyDRO also effectively preserves graph random walk properties, producing condensed graphs that achieve enhanced performance in continual graph learning. Additionally, HyDRO achieves competitive results on mainstream graph distillation benchmarks, while maintaining a strong balance between privacy and utility, and exhibiting robust resistance to noises.