Node-Specific Space Selection via Localized Geometric Hyperbolicity in Graph Neural Networks

2023-03-03 · See Hian Lee, Feng Ji, Wee Peng Tay

Many graph neural networks have been developed to learn graph representations in either Euclidean or hyperbolic space, with all nodes' representations embedded in a single space. However, a graph can have hyperbolic and Euclidean geometries at different regions of the graph. Thus, it is sub-optimal to indifferently embed an entire graph into a single space. In this paper, we explore and analyze two notions of local hyperbolicity, describing the underlying local geometry: geometric (Gromov) and model-based, to determine the preferred space of embedding for each node. The two hyperbolicities' distributions are aligned using the Wasserstein metric such that the calculated geometric hyperbolicity guides the choice of the learned model hyperbolicity. As such our model Joint Space Graph Neural Network (JSGNN) can leverage both Euclidean and hyperbolic spaces during learning by allowing node-specific geometry space selection. We evaluate our model on both node classification and link prediction tasks and observe promising performance compared to baseline models.

📄 PDF Abstract BibTeX arXiv:2303.01724

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural Network Link Prediction Node Classification

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

2025-05-04 · Jingxiang Qu, Wenhan Gao, Jiaxing Zhang, Xufeng Liu 외

3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for sc…

Efficient Localized Inference for Large Graphical Models

2017-10-28 · Jinglin Chen, Jian Peng, Qiang Liu

We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property. Given a query variable and a large graphical model, we define a much sma…

PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?

2022-08-03 · Aleksandr Kim, Guillem Brasó, Aljoša Ošep, Laura Leal-Taixé

Most (3D) multi-object tracking methods rely on appearance-based cues for data association. By contrast, we investigate how far we can get by only encoding geometric relationships between objects in 3D space as cues for …

3D Multi-Object Tracking Edge Classification Graph Neural Network Multi-Object Tracking+1

PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes

2026-01-09 · Yiming Zhou, Jiahao Wang, Mingyue Cheng, Hao Wang 외 arxiv

While collaborative forecasting on distributed time series is highly desirable, directly pooling localized datasets is often impractical due to data sharing constraints. Federated learning offers a promising alternative,…

Time Series Forecasting Federated Learning

Random Wavelet Features for Graph Kernel Machines

2026-02-17 · Valentin de Bassompierre, Jean-Charles Delvenne, Laurent Jacques arxiv

Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as node classification, link prediction, and signal reconstruction. A key g…

Graph Representation Learning Node Classification Link Prediction