# On Node Features for Graph Neural Networks

arXiv: https://arxiv.org/abs/1911.08795 · HTML: https://mlsanity.com/paper/1911.08795/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 21 of 21)

- [Not too little, not too much: a theoretical analysis of graph (over)smoothing](https://mlsanity.com/paper/2205.12156/) (2022)
- [BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks](https://mlsanity.com/paper/2204.07054/) (2022)
- [On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs](https://mlsanity.com/paper/2107.01495/) (2021)
- [Accurate Node Feature Estimation with Structured Variational Graph Autoencoder](https://mlsanity.com/paper/2206.04516/) (2022)
- [Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph](https://mlsanity.com/paper/2208.05648/) (2022)
- [Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective](https://mlsanity.com/paper/2402.04621/) (2024)
- [Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging](https://mlsanity.com/paper/2210.09840/) (2022)
- [Curriculum Guided Personalized Subgraph Federated Learning](https://mlsanity.com/paper/2509.00402/) (2025)
- [Deep Fraud Detection on Non-attributed Graph](https://mlsanity.com/paper/2110.01171/) (2021)
- [Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks](https://mlsanity.com/paper/2106.13061/) (2021)
- [Creating generalizable downstream graph models with random projections](https://mlsanity.com/paper/2302.08895/) (2023)
- [LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition using Graph Neural Networks](https://mlsanity.com/paper/2312.03756/) (2023)
- [GNN Applied to Ego-nets for Friend Suggestions](https://mlsanity.com/paper/2412.11888/) (2024)
- [Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shifts](https://mlsanity.com/paper/2504.00328/) (2025)
- [A Study on Knowledge Graph Embeddings and Graph Neural Networks for Web Of Things](https://mlsanity.com/paper/2310.14866/) (2023)
- [PropEnc: A Property Encoder for Graph Neural Networks](https://mlsanity.com/paper/2409.11554/) (2024)
- [Enhancing Future Link Prediction in Quantum Computing Semantic Networks through LLM-Initiated Node Features](https://mlsanity.com/paper/2410.04251/) (2024)
- [A graph neural network based on feature network for identifying influential nodes](https://mlsanity.com/paper/2508.01278/) (2025)
- [Discrete Diffusion-Based Model-Level Explanation of Heterogeneous GNNs with Node Features](https://mlsanity.com/paper/2508.08458/) (2025)
- [Graph Neural Networks for the Graphical Bootstrap](https://mlsanity.com/paper/2607.03109/) (2026)
- [From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning](https://mlsanity.com/paper/2609.02984/) (2026)

## 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.