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

Mark Cheung, John Shi, Oren Wright, Lavender Y. Jiang, Xujin Liu, José M. F. Moura

备注：: To be published on IEEE Signal Processing Magazine
DOI：: 10.1109/MSP.2020.3014594

英文摘要：

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.

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 in Graph Convolutional Neural Networks

Carnegie Mellon University（卡内基梅隆大学）

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.

2020-04-07cs.LGeess.SP

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

Graph Pooling with Node Proximity for Hierarchical Representation Learning

Shanghai Jiao Tong University（上海交通大学）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）

Graph neural networks have attracted wide attentions to enable representation learning of graph data in recent works. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of graph data. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Node proximity is obtained by harmonizing the kernel representat…

2020-06-19cs.LGeess.SPstat.ML

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

Hartley Spectral Pooling for Deep Learning

Harbin Institute of Technology（哈尔滨工业大学）；Peking University（北京大学）

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convolution are popular pooling methods. Since the pooling is a lossy procedure, a motivation of our work is to design a new pooling approach for less lossy in the dimensionality reduction. Inspired by the Fourier spectral pooling(FSP) proposed by Rippel et. al. [1], we present the Hartle…

2020-10-08cs.CVcs.LGeess.SP