Pooling in Graph Convolutional Neural Networks

Carnegie Mellon University（卡内基梅隆大学）

Mark Cheung, John Shi, Lavender Yao Jiang, Oren Wright, José M. F. Moura

备注：: 5 pages, 2 figures, 2019 Asilomar Conference paper

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graph-structured data problems. We empirically evaluate several pooling methods for GCNNs, and combinations of those graph pooling methods with three different architectures: GCN, TAGCN, and GraphSAGE. We confirm that graph pooling, especially DiffPool, improves classification accuracy on popular graph classification datasets and find that, on average, TAGCN achieves comparable or better accuracy than GCN and GraphSAGE, particularly for datasets with larger and sparser graph structures.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Pooling Strategies for Simplicial Convolutional Networks

Sapienza University of Rome（罗马第一大学）

The goal of this paper is to introduce pooling strategies for simplicial convolutional neural networks. Inspired by graph pooling methods, we introduce a general formulation for a simplicial pooling layer that performs: i) local aggregation of simplicial signals; ii) principled selection of sampling sets; iii) downsampling and simplicial topology adaptation. The general layer is then customized to design four different pooling strategies (i.e., max, top-k, self-attention, and separated top-k) grounded in the theory of topological signal processing. Also, we leverage the proposed layers in a hi…

2022-10-11cs.LGeess.SP

A Multi-Modal States based Vehicle Descriptor and Dilated Convolutional Social Pooling for Vehicle Trajectory Prediction

University of Shanghai Jiao Tong（上海交通大学）；School of Mechanical Engineering（机械工程学院）

Precise trajectory prediction of surrounding vehicles is critical for decision-making of autonomous vehicles and learning-based approaches are well recognized for the robustness. However, state-of-the-art learning-based methods ignore 1) the feasibility of the vehicle's multi-modal state information for prediction and 2) the mutual exclusive relationship between the global traffic scene receptive fields and the local position resolution when modeling vehicles' interactions, which may influence prediction accuracy. Therefore, we propose a vehicle-descriptor based LSTM model with the dilated con…

2020-03-07cs.AIeess.SP

卷积神经网络中最大池化特征图的平移不变性研究

On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks

Université Caen Normandie（卡昂诺曼底大学）；ENSICAEN（卡昂高等工程师学院）；CNRS（法国国家科学研究中心）；Normandie Univ（诺曼底大学）；Univ. Grenoble Alpes（格勒诺布尔大学）；Inria（法国国家信息与自动化研究所）；Grenoble INP（格勒诺布尔理工学院）；LJK（让·昆廷诺实验室）

针对CNN第一层类Gabor滤波器子采样卷积的平移敏感问题，确立最大池化近似平移不变复模的条件，推导平移不变性度量并验证，揭示滤波器频率和方向的关键作用，提升CNN数学可解释性。

2025-04-18cs.AIcs.CVeess.SP

CVGG-Net：基于复值卷积神经网络的SAR图像船舶识别

CVGG-Net: Ship Recognition for SAR Images Based on Complex-Valued Convolutional Neural Network

针对SAR图像船舶识别中忽略相位信息及复值网络池化方法不佳的问题，提出CVGG-Net，利用幅度和相位信息，并引入复区域最大池化，在实测数据集上优于实值网络。

2023-05-13eess.SP

Graph-Time Convolutional Neural Networks

Delft University of Technology（代尔夫特理工大学）

Spatiotemporal data can be represented as a process over a graph, which captures their spatial relationships either explicitly or implicitly. How to leverage such a structure for learning representations is one of the key challenges when working with graphs. In this paper, we represent the spatiotemporal relationships through product graphs and develop a first principle graph-time convolutional neural network (GTCNN). The GTCNN is a compositional architecture with each layer comprising a graph-time convolutional module, a graph-time pooling module, and a nonlinearity. We develop a graph-time c…

2021-03-02cs.AIcs.LGcs.NE

Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology

Deep learning, particularly convolutional neural networks (CNNs), have yielded rapid, significant improvements in computer vision and related domains. But conventional deep learning architectures perform poorly when data have an underlying graph structure, as in social, biological, and many other domains. This paper explores 1)how graph signal processing (GSP) can be used to extend CNN components to graphs in order to improve model performance; and 2)how to design the graph CNN architecture based on the topology or structure of the data graph.

2020-08-04eess.SP