Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

Abstract

Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on designing more effective models without considering much about the quality of the input data. In this paper, we propose self-enhanced GNN (SEG), which improves the quality of the input data using the outputs of existing GNN models for better performance on semi-supervised node classification. As graph data consist of both topology and node labels, we improve input data quality from both perspectives. For topology, we observe that higher classification accuracy can be achieved when the ratio of inter-class edges (connecting nodes from different classes) is low and propose topology update to remove inter-class edges and add intra-class edges. For node labels, we propose training node augmentation, which enlarges the training set using the labels predicted by existing GNN models. SEG is a general framework that can be easily combined with existing GNN models. Experimental results validate that SEG consistently improves the performance of well-known GNN models such as GCN, GAT and SGC across different datasets.

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Distilling the Knowledge in a Neural Network
• Inductive Representation Learning on Large Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Adversarial Attacks on Neural Networks for Graph Data
• Representation Learning on Graphs with Jumping Knowledge Networks
• Pitfalls of Graph Neural Network Evaluation
• MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
• Gated Graph Sequence Neural Networks
• Revisiting Semi-Supervised Learning with Graph Embeddings
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Geom-GCN: Geometric Graph Convolutional Networks
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
• Edge Dithering for Robust Adaptive Graph Convolutional Networks

Cited by in corpus (3)

• Predicting What You Already Know Helps: Provable Self-Supervised Learning
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks