paper-with-me

홈 › Papers

On Node Features for Graph Neural Networks

2019-11-20 · Chi Thang Duong, Thanh Dat Hoang, Ha The Hien Dang, Quoc Viet Hung Nguyen, Karl Aberer

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.

📄 PDF Abstract BibTeX arXiv:1911.08795

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural NetworkGraph Representation LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

2021-07-03 · Hejie Cui, Zijie Lu, Pan Li, Carl Yang

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 Classification

Saliency-Aware Regularized Graph Neural Network

2024-01-01 · Wenjie Pei, Weina Xu, Zongze Wu, Weichao Li 외

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+2

Recovering Missing Node Features with Local Structure-based Embeddings

2023-09-16 · Victor M. Tenorio, Madeline Navarro, Santiago Segarra, Antonio G. Marques

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 Classification

Self-supervised Guided Hypergraph Feature Propagation for Semi-supervised Classification with Missing Node Features

2023-02-16 · Chengxiang Lei, Sichao Fu, Yuetian Wang, Wenhao Qiu 외

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 Label

Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation

2023-10-10 · Anwar Said, Mudassir Shabbir, Tyler Derr, Waseem Abbas 외

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