中文
相关论文

相关论文: Modeling Graphs Beyond Hyperbolic: Graph Neural Ne…

200 篇论文

Graph representation learning has been widely studied and demonstrated effectiveness in various graph tasks. Most existing works embed graph data in the Euclidean space, while recent works extend the embedding models to hyperbolic or…

机器学习 · 计算机科学 2023-04-04 Cheng Deng , Fan Xu , Jiaxing Ding , Luoyi Fu , Weinan Zhang , Xinbing Wang

Functional magnetic resonance imaging (fMRI) reveals complex brain functional networks with hierarchical topologies crucial for cognitive processing. Standard Euclidean Graph Neural Networks (GNNs) often struggle to represent these…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Junhao Jia , Yunyou Liu , Cheng Yang , Yifei Sun , Feiwei Qin , Changmiao Wang , Yong Peng

Embedding graphs in continous spaces is a key factor in designing and developing algorithms for automatic information extraction to be applied in diverse tasks (e.g., learning, inferring, predicting). The reliability of graph embeddings…

机器学习 · 计算机科学 2023-11-30 Andrea Marinoni , Pietro Lio' , Alessandro Barp , Christian Jutten , Mark Girolami

Theoretical results from discrete geometry suggest that normed spaces can abstractly embed finite metric spaces with surprisingly low theoretical bounds on distortion in low dimensions. In this paper, inspired by this theoretical insight,…

机器学习 · 计算机科学 2023-12-05 Diaaeldin Taha , Wei Zhao , J. Maxwell Riestenberg , Michael Strube

Hyperbolic neural networks can effectively capture the inherent hierarchy of graph datasets, and consequently a powerful choice of GNNs. However, they entangle multiple incongruent (gyro-)vector spaces within a layer, which makes them…

机器学习 · 计算机科学 2023-06-07 Mehrdad Khatir , Nurendra Choudhary , Sutanay Choudhury , Khushbu Agarwal , Chandan K. Reddy

Recently there was an increasing interest in applications of graph neural networks in non-Euclidean geometry; however, are non-Euclidean representations always useful for graph learning tasks? For different problems such as node…

机器学习 · 计算机科学 2020-07-16 Max Kochurov , Sergey Ivanov , Eugeny Burnaev

Bitcoin transaction networks are large scale socio- technical systems in which activities are represented through multi-hop interaction patterns. Graph Neural Networks(GNNs) have become a widely adopted tool for analyzing such systems,…

机器学习 · 计算机科学 2026-03-18 Ankit Ghimire , Saydul Akbar Murad , Nick Rahimi

Graph embeddings, wherein the nodes of the graph are represented by points in a continuous space, are used in a broad range of Graph ML applications. The quality of such embeddings crucially depends on whether the geometry of the space…

机器学习 · 统计学 2022-02-03 Francesco Di Giovanni , Giulia Luise , Michael Bronstein

Geometric graphs are a special kind of graph with geometric features, which are vital to model many scientific problems. Unlike generic graphs, geometric graphs often exhibit physical symmetries of translations, rotations, and reflections,…

Graph-structured data provide a comprehensive description of complex systems, encompassing not only the interactions among nodes but also the intrinsic features that characterize these nodes. These features play a fundamental role in the…

物理与社会 · 物理学 2023-11-27 Roya Aliakbarisani , M. Ángeles Serrano , Marián Boguñá

High-dimensional multiplex graphs are characterized by their high number of complementary and divergent dimensions. The existence of multiple hierarchical latent relations between the graph dimensions poses significant challenges to…

机器学习 · 计算机科学 2025-01-30 Kamel Abdous , Nairouz Mrabah , Mohamed Bouguessa

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…

机器学习 · 计算机科学 2023-03-14 Tao Yu , Christopher De Sa

The class of Euclidean unit disk graphs is one of the most fundamental and well-studied graph classes with underlying geometry. In this paper, we identify this class as a special case in the broader class of hyperbolic unit disk graphs and…

数据结构与算法 · 计算机科学 2022-12-16 Thomas Bläsius , Tobias Friedrich , Maximilian Katzmann , Daniel Stephan

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 graph embeddings in…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Liyang Wang , Zeyu Zhang , Hao Tang

In the last decade or so, we have witnessed deep learning reinvigorating the machine learning field. It has solved many problems in the domains of computer vision, speech recognition, natural language processing, and various other tasks…

机器学习 · 计算机科学 2021-09-09 Lilapati Waikhom , Ripon Patgiri

Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelated to the topology, which can hardly ensure topological…

机器学习 · 计算机科学 2025-05-30 Juwei Yue , Haikuo Li , Jiawei Sheng , Xiaodong Li , Taoyu Su , Tingwen Liu , Li Guo

Recent studies have experimentally shown that we can achieve in non-Euclidean metric space effective and efficient graph embedding, which aims to obtain the vertices' representations reflecting the graph's structure in the metric space.…

机器学习 · 统计学 2023-05-16 Atsushi Suzuki , Atsushi Nitanda , Taiji Suzuki , Jing Wang , Feng Tian , Kenji Yamanishi

Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently. However, most of the existing GNN models are primarily designed for graphs in Euclidean spaces.…

机器学习 · 计算机科学 2019-12-09 Yiding Zhang , Xiao Wang , Xunqiang Jiang , Chuan Shi , Yanfang Ye

The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas. Although there are many different attempts to develop effective deep architectures for data processing on the…

计算机视觉与模式识别 · 计算机科学 2023-05-22 Ziheng Chen , Tianyang Xu , Xiao-Jun Wu , Rui Wang , Zhiwu Huang , Josef Kittler

Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message…

机器学习 · 计算机科学 2025-11-26 Md Joshem Uddin , Astrit Tola , Varin Sikand , Cuneyt Gurcan Akcora , Baris Coskunuzer