Large-Scale Learnable Graph Convolutional Networks

By Hongyang Gao, Zhengyang Wang, Shuiwang Ji. 2018

656 citations recorded by the source corpus.

Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic extraction of high-level features. The computation with filters requires a fixed number of ordered units in the receptive fields. However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations. Here, we address these challenges by proposing the learnable graph convolutional layer (LGCL). LGCL automatically selects a fixed number of neighboring nodes for each feature based on value ranking in order to transform graph data into grid-like structures in 1-D format, thereby enabling the use of regular convolutional operations on generic graphs. To enable model training on large-scale graphs, we propose a sub-graph training method to reduce the excessive memory and computational resource requirements suffered by prior methods on graph convolutions. Our experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that our methods can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network datasets. Our results also indicate that the proposed methods using sub-graph training strategy are more efficient as compared to prior approaches.

Subfields: Artificial Intelligence, Molecular Biology

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 Molecular Biology

Citations in the corpus

Auto-GNN: Neural architecture search of graph neural networks (2019, methodology): “Following the model configurations in baselines [10, 32], the training experiments are set up according to transductive learning and inductive learning, respectively.”
Explainability in Graph Neural Networks: A Taxonomic Survey (2020, background): “ing graph convolution [4], [37], [38], graph attention [39],”
AutoGraph: Automated Graph Neural Network (2020, neutral): “– LGCN [5].”
Towards Deeper Graph Neural Networks with Differentiable Group Normalization (2020, methodology): “Graph neural networks (GNNs) [1, 2, 3] have emerged as a promising tool for analyzing networked data, such as biochemical networks [4, 5], social networks [6, 7], and academic networks [8, 9].”
Deep Learning on Graphs: A Survey (2018, neutral): “LGCN [48] further proposed to simplify the sorting process by using a lexicographical order (i.e., sorting neighbors based on their hidden representation in the ﬁnal layer H L ).”
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].”
Graph Neural Networks: A Review of Methods and Applications (2018, positive): “LGCN [54] also leverages CNNs as aggregators.”
Probabilistic Dual Network Architecture Search on Graphs (2020, methodology): “The networks include Graph Attention Networks (GAT) (Veliˇckovi´c et al., 2018), learnable graph convolutional networks (LGCN) (Gao et al., 2018), and jumping knowledge networks (JKNet) (Xu et al., 2018).”
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.”
Continual Graph Learning (2020, positive): “Recently, a wide range of graph neural networks (GNNs) have been proposed to exploit the structural information underlying graphs, to potentially beneﬁt a variety of applications [Kipf and Welling, 2017; Gao et al. , 2018; Wu et al. , 2019a; Zhang et al. , 2019].”
On Explainability of Graph Neural Networks via Subgraph Explorations (2021, methodology): “…techniques have been proposed to improve the performance of deep graph models, such as graph convolution (Kipf & Welling, 2017; Gilmer et al., 2017; Gao et al., 2018; Wang et al., 2020; Yuan & Ji, 2021), graph attention (Veliˇckovi´c et al., 2018; Wang et al., 2019), and graph pooling (Yuan & Ji,…”
Graph Learning: A Survey (2021, background): “LGCN [140] Convolutional Neural Network Vertex Classification”
Self-Supervised Learning of Graph Neural Networks: A Unified Review (2021, background): “To foster methodological development and facilitate empirical comparison, we review SSL methods of GNNs and provide unified views for both contrastive and predictive methods.”
Graph Convolutional Networks with EigenPooling (2019, methodology): “The methods focusing on node representation learning have brought improvement to tasks such as node classification [14–16, 18, 22, 35] and link prediction [35] and those methods working on graph-level representation learning have mainly facilitated graph classification.”
Smoothed dilated convolutions for improved dense prediction (2018, background): “Many studies on deep learning on graphs have explored this direction, such as mixture model networks (MoNet) [28], GraphSAGE [29], graph attention networks (GAT) [30], and learnable graph convolutional networks (LGCN) [31].”
GraphNAS: Graph Neural Architecture Search with Reinforcement Learning (2019, methodology): “• LGCN [Gao et al., 2018] enables regular convolutional operations on generic graphs which archives good results in both transductive and inductive learning.”