English
Related papers

Related papers: Sign and Basis Invariant Networks for Spectral Gra…

200 papers

Spectral embedding is a powerful graph embedding technique that has received a lot of attention recently due to its effectiveness on Graph Transformers. However, from a theoretical perspective, the universal expressive power of spectral…

Machine Learning · Computer Science 2024-01-12 Jiangyan Ma , Yifei Wang , Yisen Wang

We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks. Our approach considers a restricted intermediate hypothetical model named Graph Homomorphism Model to reach the universality…

Machine Learning · Computer Science 2019-10-10 Takanori Maehara , Hoang NT

Given a signed social graph, how can we learn appropriate node representations to infer the signs of missing edges? Signed social graphs have received considerable attention to model trust relationships. Learning node representations is…

Machine Learning · Computer Science 2020-12-29 Jinhong Jung , Jaemin Yoo , U Kang

In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures…

Machine Learning · Computer Science 2022-04-28 Anwesh Bhattacharya , Marios Mattheakis , Pavlos Protopapas

We introduce a set of novel multiscale basis transforms for signals on graphs that utilize their "dual" domains by incorporating the "natural" distances between graph Laplacian eigenvectors, rather than simply using the eigenvalue ordering.…

Signal Processing · Electrical Eng. & Systems 2021-04-26 Alexander Cloninger , Haotian Li , Naoki Saito

Exploiting symmetries and invariance in data is a powerful, yet not fully exploited, way to achieve better generalisation with more efficiency. In this paper, we introduce two graph network architectures that are equivariant to several…

Machine Learning · Computer Science 2021-06-01 Francesco Farina , Emma Slade

Graph Representation Learning (GRL) has become essential for modern graph data mining and learning tasks. GRL aims to capture the graph's structural information and exploit it in combination with node and edge attributes to compute…

Machine Learning · Computer Science 2021-09-08 Marinos Poiitis , Pavlos Sermpezis , Athena Vakali

Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less dependence on data…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Sungwon Hwang , Hyungtae Lim , Hyun Myung

We propose a learning paradigm for numerical approximation of differential invariants of planar curves. Deep neural-networks' (DNNs) universal approximation properties are utilized to estimate geometric measures. The proposed framework is…

Computer Vision and Pattern Recognition · Computer Science 2022-02-15 Roy Velich , Ron Kimmel

The spectra of signed matrices have played a fundamental role in social sciences, graph theory, and control theory. In this work, we investigate the computational problems of identifying symmetric signings of matrices with natural spectral…

Discrete Mathematics · Computer Science 2017-07-25 Charles Carlson , Karthekeyan Chandrasekaran , Hsien-Chih Chang , Alexandra Kolla

We propose a generalization of transformer neural network architecture for arbitrary graphs. The original transformer was designed for Natural Language Processing (NLP), which operates on fully connected graphs representing all connections…

Machine Learning · Computer Science 2021-01-26 Vijay Prakash Dwivedi , Xavier Bresson

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separation power, that is, the ability to distinguish inputs…

Machine Learning · Computer Science 2026-02-04 Marco Pacini , Gabriele Santin , Bruno Lepri , Shubhendu Trivedi

Most existing neural networks for learning graphs address permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors coming from its neighbors. We argue that this imposes a…

Machine Learning · Computer Science 2018-01-09 Risi Kondor , Hy Truong Son , Horace Pan , Brandon Anderson , Shubhendu Trivedi

This paper proposes a family of permutation-invariant graph embeddings, generalizing the Skew Spectrum of graphs of Kondor & Borgwardt (2008). Grounded in group theory and harmonic analysis, our method introduces a new class of graph…

Machine Learning · Computer Science 2025-05-30 Armando Bellante , Martin Plávala , Alessandro Luongo

We propose a novel approach for visual representation learning called Signature-Graph Neural Networks (SGN). SGN learns latent global structures that augment the feature representation of Convolutional Neural Networks (CNN). SGN constructs…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Ali Hamdi , Flora Salim , Du Yong Kim , Xiaojun Chang

Message-passing neural networks (MPNNs) are a powerful framework for learning representations of graph-structured domains. However, weights in MPNNs act on features only, limiting their ability to capture structural patterns. We introduce a…

Machine Learning · Computer Science 2026-05-26 Florian Seiffarth

Graph Neural Networks (GNNs) have advanced relational data analysis but lack invariance learning techniques common in image classification. In node classification with GNNs, it is actually the ego-graph of the center node that is…

Machine Learning · Computer Science 2024-11-27 Qin Jiang , Chengjia Wang , Michael Lones , Yingfang Yuan , Wei Pang

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does…

Machine Learning · Computer Science 2022-02-17 Victor Garcia Satorras , Emiel Hoogeboom , Max Welling

A large body of work has investigated the properties of graph neural networks and identified several limitations, particularly pertaining to their expressive power. Their inability to count certain patterns (e.g., cycles) in a graph lies at…

Machine Learning · Computer Science 2024-06-11 Emily Jin , Michael Bronstein , İsmail İlkan Ceylan , Matthias Lanzinger

Recent successes in word embedding and document embedding have motivated researchers to explore similar representations for networks and to use such representations for tasks such as edge prediction, node label prediction, and community…

Machine Learning · Statistics 2019-04-09 Mohammad Raihanul Islam , B. Aditya Prakash , Naren Ramakrishnan