Random Laplacian Features for Learning with Hyperbolic Space
Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been developed. Existing hyperbolic networks encode geometric priors not only for the input, but also at every layer of the network. This approach involves repeatedly mapping to and from hyperbolic space, which makes these networks complicated to implement, computationally expensive to scale, and numerically unstable to train. In this paper, we propose a simpler approach: learn a hyperbolic embedding of the input, then map once from it to Euclidean space using a mapping that encodes geometric priors by respecting the isometries of hyperbolic space, and finish with a standard Euclidean network. The key insight is to use a random feature mapping via the eigenfunctions of the Laplace operator, which we show can approximate any isometry-invariant kernel on hyperbolic space. Our method can be used together with any graph neural networks: using even a linear graph model yields significant improvements in both efficiency and performance over other hyperbolic baselines in both transductive and inductive tasks.
Code (1)
Tasks
Graph LearningNode Classificationtext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Laplacian Eigenspaces, Horocycles and Neuron Models on Hyperbolic Spaces
We use hyperbolic Poisson kernel to construct the horocycle neuron model on hyperbolic spaces, which is a spectral generalization of the classical neuron model. We prove a universal approximation theorem for horocycle ne…
Hyperbolic Random Forests
Hyperbolic space is becoming a popular choice for representing data due to the hierarchical structure - whether implicit or explicit - of many real-world datasets. Along with it comes a need for algorithms capable of sol…
Geodesic Exponential Kernels: When Curvature and Linearity Conflict
We consider kernel methods on general geodesic metric spaces and provide both negative and positive results. First we show that the common Gaussian kernel can only be generalized to a positive definite kernel on a geodes…
Hyperbolic Multiplex Network Embedding with Maps of Random Walk
Recent research on network embedding in hyperbolic space have proven successful in several applications. However, nodes in real world networks tend to interact through several distinct channels. Simple aggregation or ign…
Community DetectionNetwork EmbeddingDynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction
Reconstructing both objects and hands in 3D from a single RGB image is complex. Existing methods rely on manually defined hand-object constraints in Euclidean space, leading to suboptimal feature learning. Compared with …
ObjectObject Reconstruction