Generalized Equivariance and Preferential Labeling for GNN Node Classification
This addresses a practical issue in real-world applications like anonymized social networks, though it appears incremental as it builds on prior GNN limitations.
The paper tackles the problem of node classification in graphs with unattributed nodes, where existing GNNs introduce artifacts or fail to distinguish nodes, by proposing a generalized equivariance property and Preferential Labeling technique, achieving high performance in several tasks.
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.