Walk-Steered Convolution for Graph Classification

Abstract

Graph classification is a fundamental but challenging issue for numerous real-world applications. Despite recent great progress in image/video classification, convolutional neural networks (CNNs) cannot yet cater to graphs well because of graphical non-Euclidean topology. In this work, we propose a walk-steered convolutional (WSC) network to assemble the essential success of standard convolutional neural networks as well as the powerful representation ability of random walk. Instead of deterministic neighbor searching used in previous graphical CNNs, we construct multi-scale walk fields (a.k.a. local receptive fields) with random walk paths to depict subgraph structures and advocate graph scalability. To express the internal variations of a walk field, Gaussian mixture models are introduced to encode principal components of walk paths therein. As an analogy to a standard convolution kernel on image, Gaussian models implicitly coordinate those unordered vertices/nodes and edges in a local receptive field after projecting to the gradient space of Gaussian parameters. We further stack graph coarsening upon Gaussian encoding by using dynamic clustering, such that highlevel semantics of graph can be well learned like the conventional pooling on image. The experimental results on several public datasets demonstrate the superiority of our proposed WSC method over many state-of-the-arts for graph classification.

Hierarchical Representation Learning in Graph Neural Networks With Node Decimation Pooling

“…The results obtained by Dense, instead, help to quantify how much additional information is brought by the graph structure compared to considering the node features alone. While recent graph kernels [48], [49], [50] and GNN architectures [51], [52] could be considered as further baselines for graph classification, the focus of our analysis and discussion is on graph pooling operators and, therefore, we point the interested reader towards the referenced papers.…”

Context-Dependent Diffusion Network for Visual Relationship Detection

“…The latter explicitly model spatial neighborhood relationships through sorting or aggregating neighbor nodes. For examples, diffusion convolution neural network (CNN) [2] performed a diffusion process across each nodes; PSCN [29] sorted neighbors via edge connections and then performed convolution on sorted nodes; NgramCNN [26] serialized each graph by using the concept of n-gram block; GraphSAGE [11] and EP-B [8] aggregated or propagated local neighbor nodes; WSC [13] attempted to define "directional" convolution on random walks by introducing Gaussian mixture models into local walk fields. More recently, Zhao et.al [43] attempted to generalize the ideas/structures of the standard convolution neural network into graph convoution networks.…”

Weed Detection in Images of Carrot Fields Based on Improved YOLO v4

“…With the recent development of deep learning (DL), convolutional neural network (CNN) has been effectively applied in machine vision [5][6]. Major breakthroughs have been achieved in CNN applications to image recognition [7][8], semantic segmentation [9][10] and object detection [11][12]. Thanks to its strong representation ability of image features, the CNN has been increasingly applied to agriculture.…”