English
Related papers

Related papers: Fully Hyperbolic Neural Networks

200 papers

We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN). It applies given spatial transformations directly to a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Kyle Olszewski , Sergey Tulyakov , Oliver Woodford , Hao Li , Linjie Luo

Graph convolutional networks (GCNs) have received considerable research attention recently. Most GCNs learn the node representations in Euclidean geometry, but that could have a high distortion in the case of embedding graphs with…

Machine Learning · Computer Science 2021-04-16 Yiding Zhang , Xiao Wang , Chuan Shi , Nian Liu , Guojie Song

Data representation in non-Euclidean spaces has proven effective for capturing hierarchical and complex relationships in real-world datasets. Hyperbolic spaces, in particular, provide efficient embeddings for hierarchical structures. This…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Jacob Fein-Ashley , Ethan Feng , Minh Pham

Various neuroimaging studies suffer from small sample size problem which often limit their reliability. Meta-analysis addresses this challenge by aggregating findings from different studies to identify consistent patterns of brain activity.…

Machine Learning · Computer Science 2025-11-27 Seunghun Baek , Jaejin Lee , Jaeyoon Sim , Minjae Jeong , Won Hwa Kim

Recent papers in the graph machine learning literature have introduced a number of approaches for hyperbolic representation learning. The asserted benefits are improved performance on a variety of graph tasks, node classification and link…

Machine Learning · Computer Science 2025-02-26 Isay Katsman , Anna Gilbert

The human brain displays a complex network topology, whose structural organization is widely studied using diffusion tensor imaging. The original geometry from which emerges the network topology is known, as well as the localization of the…

Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds,…

Machine Learning · Computer Science 2021-04-15 Jindou Dai , Yuwei Wu , Zhi Gao , Yunde Jia

Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling…

Machine Learning · Computer Science 2025-07-24 Tao Xu , Dung-Yang Lee , Momiao Xiong

We introduce Mercator, a reliable embedding method to map real complex networks into their hyperbolic latent geometry. The method assumes that the structure of networks is well described by the Popularity$\times$Similarity…

Physics and Society · Physics 2019-04-25 Guillermo García-Pérez , Antoine Allard , M. Ángeles Serrano , Marián Boguñá

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…

Physics and Society · Physics 2023-11-27 Roya Aliakbarisani , M. Ángeles Serrano , Marián Boguñá

Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility,…

Machine Learning · Computer Science 2025-01-03 Vinod Kumar Chauhan , Jiandong Zhou , Ping Lu , Soheila Molaei , David A. Clifton

Recently, hyperbolic space has risen as a promising alternative for semi-supervised graph representation learning. Many efforts have been made to design hyperbolic versions of neural network operations. However, the inspiring geometric…

Machine Learning · Computer Science 2022-01-24 Jiahong Liu , Menglin Yang , Min Zhou , Shanshan Feng , Philippe Fournier-Viger

Signed network embedding methods aim to learn vector representations of nodes in signed networks. However, existing algorithms only managed to embed networks into low-dimensional Euclidean spaces whereas many intrinsic features of signed…

Machine Learning · Computer Science 2021-07-16 Wenzhuo Song , Hongxu Chen , Xueyan Liu , Hongzhe Jiang , Shengsheng Wang

Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view…

Machine Learning · Computer Science 2024-12-18 Mengfan Li , Xuanhua Shi , Chenqi Qiao , Teng Zhang , Hai Jin

Embedding the data in hyperbolic spaces can preserve complex relationships in very few dimensions, thus enabling compact models and improving efficiency of machine learning (ML) algorithms. The underlying idea is that hyperbolic…

Machine Learning · Computer Science 2025-01-14 Vladimir Jaćimović

Complex network topologies and hyperbolic geometry seem specularly connected, and one of the most fascinating and challenging problems of recent complex network theory is to map a given network to its hyperbolic space. The Popularity…

Disordered Systems and Neural Networks · Physics 2017-12-08 Josephine Maria Thomas , Alessandro Muscoloni , Sara Ciucci , Ginestra Bianconi , Carlo Vittorio Cannistraci

Artificial neural networks (ANNs) were inspired by the architecture and functions of the human brain and have revolutionised the field of artificial intelligence (AI). Inspired by studies on the latent geometry of the brain, in this…

Neurons and Cognition · Quantitative Biology 2025-02-04 Alexander Joseph , Nathan Francis , Meijke Balay

Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks. The…

Machine Learning · Statistics 2018-09-20 Benjamin Paul Chamberlain , James Clough , Marc Peter Deisenroth

Machine-learning function representations such as neural networks have proven to be excellent constructs for constitutive modeling due to their flexibility to represent highly nonlinear data and their ability to incorporate constitutive…

Soft Condensed Matter · Physics 2024-04-25 Jan N. Fuhg , Asghar Jadoon , Oliver Weeger , D. Thomas Seidl , Reese E. Jones

The hyperbolic random graph model (HRG) has proven useful in the analysis of scale-free networks, which are ubiquitous in many fields, from social network analysis to biology. However, working with this model is algorithmically and…

Computational Geometry · Computer Science 2019-01-08 Eryk Kopczyński , Dorota Celińska-Kopczyńska