Graph Classification using Structural Attention

Lee, John Boaz; Rossi, Ryan A.; Kong, Xiangnan

doi:10.1145/3219819.3219980

Cited by 226 publications

(110 citation statements)

References 17 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…Apart from applying graph attention spatially, GeniePath [55] further proposes an LSTMlike gating mechanism to control information flow across graph convolutional layers. There are other graph attention models which might be of interest [88], [89]. However, they do not belong to the ConvGNN framework.…”

Section: B Spatial-based Convgnnsmentioning

confidence: 99%

A Comprehensive Survey on Graph Neural Networks

Pan

Chen

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

6,220

2,977

View full text Add to dashboard Cite

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.

show abstract

Section: B Spatial-based Convgnnsmentioning

confidence: 99%

A Comprehensive Survey on Graph Neural Networks

Pan

Chen

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

6,220

2,977

View full text Add to dashboard Cite

show abstract

“…Graph convolutional networks have a great expressive power to learn the graph representations and have achieved a superior performance in a wide range of tasks and applications. Note that in the past few years, many other types of graph neural networks have been proposed, including (but are not limited to): (1) graph auto-encoder [21], (2) graph generative model [22,23], (3) graph attention model [24,25], and (4) graph recurrent neural networks [26,27].…”

mentioning

confidence: 99%

Graph convolutional networks: a comprehensive review

et al. 2019

View full text Add to dashboard Cite

Graphs naturally arise in many real-world applications, including social analysis [1], fraud detection [2, 3], traffic prediction [4], computer vision [5], and many more. By representing the data as graphs, the structural information can be encoded to model the relations among entities, and furnish more promising insights underlying the data. For example, in a transportation network, nodes are often the sensors and edges represent the spatial proximity among sensors. In addition to the temporal information provided by the sensors themselves, the graph structure modeled by the spatial correlations leads to a prominent improvement in the traffic prediction problem [4]. Moreover, by

show abstract

“…None of these models are designed to select the optimal movement trajectory (path) for node classi cation. e GAM (Graph A ention Model) proposed by Lee et al [16] is an RNN model for graph classi cation (not node classi cation), through a ention on the graph structural composition. e graph classi cation di ers from node classi cation on the prediction goal.…”

Section: Reinforcement On Graph-structured Datamentioning

confidence: 99%

Recurrent Attention Walk for Semi-supervised Classification

Akujuobi

Zhang

Han³

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

In this paper, we study the graph-based semi-supervised learning for classifying nodes in a ributed networks, where the nodes and edges possess content information. Recent approaches like graph convolution networks and a ention mechanisms have been proposed to ensemble the rst-order neighbors and incorporate the relevant neighbors. However, it is costly (especially in memory) to consider all neighbors without a prior di erentiation. We propose to explore the neighborhood in a reinforcement learning se ing and nd a walk path well-tuned for classifying the unlabelled target nodes. We let an agent (of node classi cation task) walk over the graph and decide where to direct to maximize classi cation accuracy. We de ne the graph walk as a partially observable Markov decision process (POMDP). e proposed method is exible for working in both transductive and inductive se ing. Extensive experiments on four datasets demonstrate that our proposed method outperforms several state-of-the-art methods. Several case studies also illustrate the meaningful movement trajectory made by the agent.

show abstract

Graph Classification using Structural Attention

Cited by 226 publications

References 17 publications

A Comprehensive Survey on Graph Neural Networks

A Comprehensive Survey on Graph Neural Networks

Graph convolutional networks: a comprehensive review

Recurrent Attention Walk for Semi-supervised Classification

Contact Info

Product

Resources

About