The paper derives a per-class generalization bound for imbalanced transductive node classification and introduces UPL, a pseudo-labeling algorithm that filters minority-class pseudo-labels by entropy variance across edge-perturbed graphs.
Towards Understanding the Generalization of Graph Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Graph neural networks (GNNs) are the most widely adopted model in graph-structured data oriented learning and representation. Despite their extraordinary success in real-world applications, understanding their working mechanism by theory is still on primary stage. In this paper, we move towards this goal from the perspective of generalization. To be specific, we first establish high probability bounds of generalization gap and gradients in transductive learning with consideration of stochastic optimization. After that, we provide high probability bounds of generalization gap for popular GNNs. The theoretical results reveal the architecture specific factors affecting the generalization gap. Experimental results on benchmark datasets show the consistency between theoretical results and empirical evidence. Our results provide new insights in understanding the generalization of GNNs.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UPL: Uncertainty-aware Pseudo-labeling for Imbalance Transductive Node Classification
The paper derives a per-class generalization bound for imbalanced transductive node classification and introduces UPL, a pseudo-labeling algorithm that filters minority-class pseudo-labels by entropy variance across edge-perturbed graphs.