Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning
Finding meaningful representations and distances of hierarchical data is important in many fields. This paper presents a new method for hierarchical data embedding and distance. Our method relies on combining diffusion geometry, a central approach to manifold learning, and hyperbolic geometry. Specifically, using diffusion geometry, we build multi-scale densities on the data, aimed to reveal their hierarchical structure, and then embed them into a product of hyperbolic spaces. We show theoretically that our embedding and distance recover the underlying hierarchical structure. In addition, we demonstrate the efficacy of the proposed method and its advantages compared to existing methods on graph embedding benchmarks and hierarchical datasets.
Code (1)
Tasks
Graph EmbeddingRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RegD: Hierarchical Embeddings via Distances over Geometric Regions
Hierarchical data are common in many domains like life sciences and e-commerce, and their embeddings often play a critical role. Although hyperbolic embeddings offer a grounded approach to representing hierarchical struc…
Hyperbolic Distance Matrices
Hyperbolic space is a natural setting for mining and visualizing data with hierarchical structure. In order to compute a hyperbolic embedding from comparison or similarity information, one has to solve a hyperbolic dista…
Hyperbolic Graph Diffusion Model
Diffusion generative models (DMs) have achieved promising results in image and graph generation. However, real-world graphs, such as social networks, molecular graphs, and traffic graphs, generally share non-Euclidean to…
Graph GenerationmodelHSG: Hyperbolic Scene Graph
Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene gra…
Representation LearningContrastive LearningHyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies
Hierarchical data arise in countless domains, from biological taxonomies and organizational charts to legal codes and knowledge graphs. Residual Quantization (RQ) is widely used to generate discrete, multitoken represent…
Inductive BiasKnowledge GraphsQuantizationRepresentation Learning