Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
This addresses a gap in graph-based machine learning for data valuation, offering an efficient and interpretable method, though it appears incremental as it builds on existing Shapley value techniques.
The paper tackles the problem of evaluating the importance of neighbors for testing nodes in Graph Neural Networks (GNNs) without test labels, proposing Shapley-Guided Utility Learning (SGUL) which outperforms existing baselines in inductive and transductive settings on diverse graph datasets.
Graph Neural Networks (GNNs) have demonstrated remarkable performance in various graph-based machine learning tasks, yet evaluating the importance of neighbors of testing nodes remains largely unexplored due to the challenge of assessing data importance without test labels. To address this gap, we propose Shapley-Guided Utility Learning (SGUL), a novel framework for graph inference data valuation. SGUL innovatively combines transferable data-specific and modelspecific features to approximate test accuracy without relying on ground truth labels. By incorporating Shapley values as a preprocessing step and using feature Shapley values as input, our method enables direct optimization of Shapley value prediction while reducing computational demands. SGUL overcomes key limitations of existing methods, including poor generalization to unseen test-time structures and indirect optimization. Experiments on diverse graph datasets demonstrate that SGUL consistently outperforms existing baselines in both inductive and transductive settings. SGUL offers an effective, efficient, and interpretable approach for quantifying the value of test-time neighbors.