mlsanityData to 7 Oct 2026

On Node Features for Graph Neural Networks

arXiv 1911.08795 ↗First posted 20 Nov 2019cs.LG stat.MLcited by 20

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 3; 2024: 4; 2025: 4; 2026: 1.

20 papers.

Sort:

By area:

  1. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  2. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  3. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  4. 2022Accurate Node Feature Estimation with Structured Variational Graph Autoencodercited by 12
  5. 2022Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graphcited by 10
  6. 2024Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspectivecited by 9
  7. 2022Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Taggingcited by 4
  8. 2025Curriculum Guided Personalized Subgraph Federated Learningcited by 4
  9. 2021Deep Fraud Detection on Non-attributed Graphcited by 3
  10. 2021Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networkscited by 1
  11. 2023Creating generalizable downstream graph models with random projectionscited by 1
  12. 2023LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition using Graph Neural Networkscited by 1
8 more
  1. 2024GNN Applied to Ego-nets for Friend Suggestionscited by 1
  2. 2025Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shiftscited by 1
  3. 2023A Study on Knowledge Graph Embeddings and Graph Neural Networks for Web Of Thingscited by 0
  4. 2024PropEnc: A Property Encoder for Graph Neural Networkscited by 0
  5. 2024Enhancing Future Link Prediction in Quantum Computing Semantic Networks through LLM-Initiated Node Featurescited by 0
  6. 2025A graph neural network based on feature network for identifying influential nodescited by 0
  7. 2025Discrete Diffusion-Based Model-Level Explanation of Heterogeneous GNNs with Node Featurescited by 0
  8. 2026Graph Neural Networks for the Graphical Bootstrapcited by 0