English
Related papers

Related papers: Breaking Symmetry Bottlenecks in GNN Readouts

200 papers

Current graph representation learning techniques use Graph Neural Networks (GNNs) to extract features from dataset embeddings. In this work, we examine the quality of these embeddings and assess how changing them can affect the accuracy of…

Machine Learning · Computer Science 2022-11-30 S. Purchase , A. Zhao , R. D. Mullins

Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incorporating noise can degrade performance, while architectures…

Machine Learning · Computer Science 2025-02-05 Xiyuan Wang , Muhan Zhang

Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks. Yet, obtaining an accurate representation for a graph further requires a pooling function…

Machine Learning · Computer Science 2021-06-29 Jinheon Baek , Minki Kang , Sung Ju Hwang

Graph convolutional neural networks (GCNNs) learn compositional representations from network data by nesting linear graph convolutions into nonlinearities. In this work, we approach GCNNs from a state-space perspective revealing that the…

Signal Processing · Electrical Eng. & Systems 2021-02-15 Luana Ruiz , Fernando Gama , Alejandro Ribeiro , Elvin Isufi

Graph neural networks (GNNs) are effective models for representation learning on relational data. However, standard GNNs are limited in their expressive power, as they cannot distinguish graphs beyond the capability of the Weisfeiler-Leman…

Machine Learning · Computer Science 2021-06-07 Ralph Abboud , İsmail İlkan Ceylan , Martin Grohe , Thomas Lukasiewicz

Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade performance due to their reliance on spatially…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Nuria Alabau-Bosque , Jorge Vila-Tomas , Paula Dauden-Oliver , Valero Laparra , Jesus Malo

Network data can be conveniently modeled as a graph signal, where data values are assigned to nodes of a graph that describes the underlying network topology. Successful learning from network data is built upon methods that effectively…

Machine Learning · Computer Science 2021-05-26 Fernando Gama , Elvin Isufi , Geert Leus , Alejandro Ribeiro

Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling methods commonly consist of two stages: selecting top-ranked nodes…

Machine Learning · Computer Science 2023-11-22 Chuang Liu , Wenhang Yu , Kuang Gao , Xueqi Ma , Yibing Zhan , Jia Wu , Bo Du , Wenbin Hu

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn…

Machine Learning · Computer Science 2020-02-06 Seongjun Yun , Minbyul Jeong , Raehyun Kim , Jaewoo Kang , Hyunwoo J. Kim

Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification. However, it is…

Machine Learning · Computer Science 2021-10-19 Langzhang Liang , Cuiyun Gao , Shiyi Chen , Shishi Duan , Yu pan , Junjin Zheng , Lei Wang , Zenglin Xu

We precisely characterize the expressivity of computable Recurrent Graph Neural Networks (recurrent GNNs). We prove that recurrent GNNs with finite-precision parameters, sum aggregation, and ReLU activation, can compute any graph algorithm…

Machine Learning · Computer Science 2026-03-17 Eran Rosenbluth , Martin Grohe

Graph Neural Networks (GNNs) face fundamental limitations in expressivity and capturing structural heterogeneity. Standard message-passing architectures are constrained by the 1-dimensional Weisfeiler-Leman (1-WL) test, unable to…

Machine Learning · Computer Science 2026-05-19 Asela Hevapathige , Ahad N. Zehmakan , Asiri Wijesinghe , Saman Halgamuge

We propose a deep Graph Neural Network (GNN) model that alternates two types of layers. The first type is inspired by Reservoir Computing (RC) and generates new vertex features by iterating a non-linear map until it converges to a fixed…

Machine Learning · Computer Science 2021-04-13 Filippo Maria Bianchi , Claudio Gallicchio , Alessio Micheli

Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution shifts between training and testing graphs, inducing the degeneration of the generalization ability of GNNs on Out-Of-Distribution (OOD) settings. The…

Machine Learning · Computer Science 2024-03-12 Shaohua Fan , Xiao Wang , Chuan Shi , Peng Cui , Bai Wang

Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed…

Machine Learning · Computer Science 2021-06-14 Seongjun Yun , Minbyul Jeong , Sungdong Yoo , Seunghun Lee , Sean S. Yi , Raehyun Kim , Jaewoo Kang , Hyunwoo J. Kim

This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs of a GNN on the input graph, with some of the nodes randomly…

Machine Learning · Computer Science 2021-11-12 Pál András Papp , Karolis Martinkus , Lukas Faber , Roger Wattenhofer

Graph neural networks (GNNs) have been widely used in graph-related contexts. It is known that the separation power of GNNs is equivalent to that of the Weisfeiler-Lehman (WL) test; hence, GNNs are imperfect at identifying all…

Machine Learning · Computer Science 2025-02-07 Ziang Chen , Qiao Zhang , Runzhong Wang

To deepen our understanding of graph neural networks, we investigate the representation power of Graph Convolutional Networks (GCN) through the looking glass of graph moments, a key property of graph topology encoding path of various…

Machine Learning · Computer Science 2019-11-04 Nima Dehmamy , Albert-László Barabási , Rose Yu

The complicated syntax structure of natural language is hard to be explicitly modeled by sequence-based models. Graph is a natural structure to describe the complicated relation between tokens. The recent advance in Graph Neural Networks…

Computation and Language · Computer Science 2019-09-19 Wei Li , Shuheng Li , Shuming Ma , Yancheng He , Deli Chen , Xu Sun

Oversmoothing is a central challenge of building more powerful Graph Neural Networks (GNNs). While previous works have only demonstrated that oversmoothing is inevitable when the number of graph convolutions tends to infinity, in this…

Machine Learning · Computer Science 2023-03-02 Xinyi Wu , Zhengdao Chen , William Wang , Ali Jadbabaie
‹ Prev 1 8 9 10 Next ›