Generalized Equivariance and Preferential Labeling for GNN Node Classification


  • Zeyu Sun Peking University
  • Wenjie Zhang Peking University
  • Lili Mou University of Alberta
  • Qihao Zhu Peking University
  • Yingfei Xiong Peking University
  • Lu Zhang Peking University



Machine Learning (ML)


Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content. However, graphs with unattributed nodes widely exist in real-world applications (e.g., anonymized social networks). Previous GNNs either assign random labels to nodes (which introduces artefacts to the GNN) or assign one embedding to all nodes (which fails to explicitly distinguish one node from another). Further, when these GNNs are applied to unattributed node classification problems, they have an undesired equivariance property, which are fundamentally unable to address the data with multiple possible outputs. In this paper, we analyze the limitation of existing approaches to node classification problems. Inspired by our analysis, we propose a generalized equivariance property and a Preferential Labeling technique that satisfies the desired property asymptotically. Experimental results show that we achieve high performance in several unattributed node classification tasks.




How to Cite

Sun, Z., Zhang, W., Mou, L., Zhu, Q., Xiong, Y., & Zhang, L. (2022). Generalized Equivariance and Preferential Labeling for GNN Node Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8395-8403.



AAAI Technical Track on Machine Learning III