This paper introduces a comprehensive framework to characterize the topology awareness of GNNs across any topological feature, investigating its effects on GNN generalization performance.
Our analysis reveals a critical insight: improving the topology awareness of GNNs may inadvertently lead to unfair generalization across structural groups, which might not be desired in some scenarios.
Despite the empirical successes of GNNs, the influence of topology awareness on generalization performance remains unexplored, particularly for node-level tasks that diverge from the I.I.D. assumption.
The precise definition and characterization of the topology awareness of GNNs, especially concerning different topological features, are still unclear and require further exploration.
#graph-neural-networks #topology-awareness #generalization-performance #machine-learning #computer-vision
Collection
[
|
...
]