Graph Convolutional Networks with EigenPooling

By Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang. Knowledge Discovery and Data Mining, 2019

366 citations recorded by the source corpus.

Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks such as node classification and link prediction. To apply graph neural networks for the graph classification task, approaches to generate thegraph representation from node representations are demanded. A common way is to globally combine the node representations. However, rich structural information is overlooked. Thus a hierarchical pooling procedure is desired to preserve the graph structure during the graph representation learning. There are some recent works on hierarchically learning graph representation analogous to the pooling step in conventional convolutional neural (CNN) networks. However, the local structural information is still largely neglected during the pooling process. In this paper, we introduce a pooling operator $\pooling$ based on graph Fourier transform, which can utilize the node features and local structures during the pooling process. We then design pooling layers based on the pooling operator, which are further combined with traditional GCN convolutional layers to form a graph neural network framework $\m$ for graph classification. Theoretical analysis is provided to understand $\pooling$ from both local and global perspectives. Experimental results of the graph classification task on $6$ commonly used benchmarks demonstrate the effectiveness of the proposed framework.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/8ccbd4898fd7cecac6823e7caa15c74fca670fbe

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

Citations in the corpus

AM-GCN: Adaptive Multi-channel Graph Convolutional Networks (2020, background): “5 RELATEDWORK Recently, graph convolutional network (GCN) models [4, 9, 17, 23, 33, 35] have been widely studied.”
Pooling Architecture Search for Graph Classification (2021, methodology): “Besides, GMN [20] proposes one memory layer to jointly learn node representations and coarsen graph, MinCutPool [2] and EigenPool [28] focus on learning assignment functions in the frequency domain.”
Graph Random Neural Networks for Semi-Supervised Learning on Graphs (2020, methodology): “lorations to representation learning. A wide variety of graph applications have benefited from this shift, such as node classification [10, 27], link prediction [45, 48, 50], and graph classification [32, 46]. The essential procedure in GNNs is the feature propagation, which is usually performed by ”
Machine Learning for Synthetic Data Generation: a Review (2023, neutral): “Unlike traditional sequential models like RNNs (Recurrent Neural Networks) and LSTMs (Long Short-Term Memory), the Transformer model leverages a unique mechanism called self-attention, which allows it to capture long-range dependencies and relationships within the input data more effectively.”
Towards Deeper Graph Neural Networks (2020, background): “Great successes have been achieved for many applications, such as node classification [7, 9, 11, 12, 21, 30, 31, 33], graph classification [6, 8, 14, 18, 32, 34, 35, 38] and link prediction [1, 36, 37].”
ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations (2019, methodology): “Since then, new data-driven pooling methods have been proposed; both spectral (Ma et al. 2019; Dhillon, Guan, and Kulis 2007) and non-spectral (Ying et al. 2018; Gao and Ji 2019).”
Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings (2020, background): “Recent years have seen a significantly growing amount of interest in graph neural networks (GNNs), especially on efforts devoted to developing more effective GNNs for node classification [27, 34, 16, 49], graph classification [57, 41] and graph generation [45, 35, 58].”