paper-with-me

홈 › Papers

Spatial Graph Convolutional Networks

2019-09-11 · Tomasz Danel, Przemysław Spurek, Jacek Tabor, Marek Śmieja, Łukasz Struski, Agnieszka Słowik, Łukasz Maziarka

Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds. However, GCNs lack the ability to take into account the ordering of node neighbors, even when there is a geometric interpretation of the graph vertices that provides an order based on their spatial positions. To remedy this issue, we propose Spatial Graph Convolutional Network (SGCN) which uses spatial features to efficiently learn from graphs that can be naturally located in space. Our contribution is threefold: we propose a GCN-inspired architecture which (i) leverages node positions, (ii) is a proper generalization of both GCNs and Convolutional Neural Networks (CNNs), (iii) benefits from augmentation which further improves the performance and assures invariance with respect to the desired properties. Empirically, SGCN outperforms state-of-the-art graph-based methods on image classification and chemical tasks.

📄 PDF Abstract BibTeX arXiv:1909.05310

Code (2)

gmum/geo-gcn 공식 구현 pytorch
lyqcom/sgcn mindspore

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

2019-04-06 · Lu Bail, Lixin Cui, Yuhang Jiao, Luca Rossi 외

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-…

General ClassificationGraph Classification

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning

2024-01-13 · Ling Wang, Ye Yuan

Dynamic graphs (DG) describe dynamic interactions between entities in many practical scenarios. Most existing DG representation learning models combine graph convolutional network and sequence neural network, which model…

Graph Representation LearningRepresentation Learning

Adaptive Cross-Attention-Driven Spatial-Spectral Graph Convolutional Network for Hyperspectral Image Classification

2022-04-12 · Jin-Yu Yang, Heng-Chao Li, Wen-Shuai Hu, Lei Pan 외

Recently, graph convolutional networks (GCNs) have been developed to explore spatial relationship between pixels, achieving better classification performance of hyperspectral images (HSIs). However, these methods fail to…

Graph AttentionHyperspectral Image Classificationimage-classificationImage Classification

Graph Convolutional Neural Networks based on Quantum Vertex Saliency

2018-09-04 · Lu Bai, Yuhang Jiao, Luca Rossi, Lixin Cui 외

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neu…

General ClassificationGraph Classification

Modeling of spatially embedded networks via regional spatial graph convolutional networks

2024-06-20 · Computer-Aided Civil and Infrastructure Engineering 2024 6 · Xudong Fan, Jürgen Hackl

Efficient representation of complex infrastructure systems is crucial for system-level management tasks, such as edge prediction, component classification, and decision-making. However, the complex interactions between t…

Component ClassificationDecision MakingMultimodal Deep LearningRepresentation Learning