English
Related papers

Related papers: Random Search Neural Networks for Efficient and Ex…

200 papers

We revisit a simple model class for machine learning on graphs, where a random walk on a graph produces a machine-readable record, and this record is processed by a deep neural network to directly make vertex-level or graph-level…

Machine Learning · Computer Science 2025-03-06 Jinwoo Kim , Olga Zaghen , Ayhan Suleymanzade , Youngmin Ryou , Seunghoon Hong

In recent years, graph neural networks (GNNs) have gained increasing popularity and have shown very promising results for data that are represented by graphs. The majority of GNN architectures are designed based on developing new…

Machine Learning · Statistics 2021-10-05 Anahita Iravanizad , Edgar Ivan Sanchez Medina , Martin Stoll

Rethink convolution-based graph neural networks (GNN) -- they characteristically suffer from limited expressiveness, over-smoothing, and over-squashing, and require specialized sparse kernels for efficient computation. Here, we design a…

Machine Learning · Computer Science 2024-10-01 Yuanqing Wang , Kyunghyun Cho

Graph data, with its structurally variable nature, represents complex real-world phenomena like chemical compounds, protein structures, and social networks. Traditional Graph Neural Networks (GNNs) primarily utilize the message-passing…

Machine Learning · Computer Science 2025-02-05 Jianming Huang , Hiroyuki Kasai

Graph neural networks (GNNs) have recently become the standard approach for learning with graph-structured data. Prior work has shed light into their potential, but also their limitations. Unfortunately, it was shown that standard GNNs are…

Machine Learning · Computer Science 2023-06-12 Gaspard Michel , Giannis Nikolentzos , Johannes Lutzeyer , Michalis Vazirgiannis

In the modern age of social media and networks, graph representations of real-world phenomena have become an incredibly useful source to mine insights. Often, we are interested in understanding how entities in a graph are interconnected.…

Machine Learning · Computer Science 2021-12-16 Aneesh Komanduri , Justin Zhan

Graph neural networks (GNNs) have achieved outstanding performance in learning graph-structured data and various tasks. However, many current GNNs suffer from three common problems when facing large-size graphs or using a deeper structure:…

Machine Learning · Computer Science 2021-05-05 Jiyang Bai , Yuxiang Ren , Jiawei Zhang

Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explainable AI approaches are not applicable. To a large extent,…

Graph embedding has recently gained momentum in the research community, in particular after the introduction of random walk and neural network based approaches. However, most of the embedding approaches focus on representing the local…

Machine Learning · Computer Science 2020-02-19 Joerg Schloetterer , Martin Wehking , Fatemeh Salehi Rizi , Michael Granitzer

An important part of many machine learning workflows on graphs is vertex representation learning, i.e., learning a low-dimensional vector representation for each vertex in the graph. Recently, several powerful techniques for unsupervised…

Machine Learning · Computer Science 2019-01-23 Hooman Peiro Sajjad , Andrew Docherty , Yuriy Tyshetskiy

Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs. In contrast, graph transformers (GTs) enable global information exchange but often oversimplify the…

Machine Learning · Computer Science 2024-10-08 Dexiong Chen , Till Hendrik Schulz , Karsten Borgwardt

Node-level random walk has been widely used to improve Graph Neural Networks. However, there is limited attention to random walk on edge and, more generally, on $k$-simplices. This paper systematically analyzes how random walk on different…

Machine Learning · Computer Science 2023-10-31 Cai Zhou , Xiyuan Wang , Muhan Zhang

In this paper, we present a novel approach based on the random walk process for finding meaningful representations of a graph model. Our approach leverages the transient behavior of many short random walks with novel initialization…

Social and Information Networks · Computer Science 2018-05-14 Lin Li , William M. Campbell , Rajmonda S. Caceres

Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, and robustness. Layer-wise relevance propagation for GNNs (GNN-LRP) evaluates the…

Machine Learning · Computer Science 2026-05-25 Ping Xiong , Thomas Schnake , Michael Gastegger , Grégoire Montavon , Klaus-Robert Müller , Shinichi Nakajima

In recent years, new neural network architectures designed to operate on graph-structured data have pushed the state-of-the-art in the field. A large set of these architectures utilize a form of classical random walks to diffuse…

Quantum Physics · Physics 2018-06-18 Stefan Dernbach , Arman Mohseni-Kabir , Siddharth Pal , Don Towsley , Miles Gepner

Many real-world datasets have an underlying dynamic graph structure, where entities and their interactions evolve over time. Machine learning models should consider these dynamics in order to harness their full potential in downstream…

Machine Learning · Computer Science 2024-02-20 Ahmad Naser Eddin , Jacopo Bono , David Aparício , Hugo Ferreira , João Ascensão , Pedro Ribeiro , Pedro Bizarro

While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to three layers. Deep GNNs fundamentally need to address: 1).…

Node classification using Graph Neural Networks (GNNs) has been widely applied in various practical scenarios, such as predicting user interests and detecting communities in social networks. However, recent studies have shown that…

Machine Learning · Computer Science 2024-08-14 Shuqi He , Jun Zhuang , Ding Wang , Jun Song

Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Typical HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Recent…

Machine Learning · Computer Science 2024-09-04 Jun Hu , Bryan Hooi , Bingsheng He

Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with…

Computer Vision and Pattern Recognition · Computer Science 2017-05-09 Gedas Bertasius , Lorenzo Torresani , Stella X. Yu , Jianbo Shi
‹ Prev 1 2 3 10 Next ›