On Node Features for Graph Neural Networks
Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkGraph Representation LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where superior performance is mainly established when natural node features are a…
ClassificationGraph ClassificationNode ClassificationSaliency-Aware Regularized Graph Neural Network
The crux of graph classification lies in the effective representation learning for the entire graph. Typical graph neural networks focus on modeling the local dependencies when aggregating features of neighboring nodes, …
ClassificationGraph ClassificationGraph Neural NetworkRepresentation Learning+2Recovering Missing Node Features with Local Structure-based Embeddings
Node features bolster graph-based learning when exploited jointly with network structure. However, a lack of nodal attributes is prevalent in graph data. We present a framework to recover completely missing node features…
Graph ClassificationSelf-supervised Guided Hypergraph Feature Propagation for Semi-supervised Classification with Missing Node Features
Graph neural networks (GNNs) with missing node features have recently received increasing interest. Such missing node features seriously hurt the performance of the existing GNNs. Some recent methods have been proposed t…
Pseudo LabelEnhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation
Graph Neural Networks (GNNs) have shown remarkable merit in performing various learning-based tasks in complex networks. The superior performance of GNNs often correlates with the availability and quality of node-level f…
Graph ClassificationGraph EmbeddingNode Classification