Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees
Abstract
Graph-based semi-supervised learning is a powerful paradigm in machine learning for modeling and exploiting the underlying graph structure that captures the relationship between labeled and unlabeled data. A large number of classical as well as modern deep learning based algorithms have been proposed for this problem, often having tunable hyperparameters. We initiate a formal study of tuning algorithm hyperparameters from parameterized algorithm families for this problem. We obtain novel pseudo-dimension upper bounds for hyperparameter selection in three classical label propagation-based algorithm families, where is the number of nodes, implying bounds on the amount of data needed for learning provably good parameters. We further provide matching pseudo-dimension lower bounds, thus asymptotically characterizing the learning-theoretic complexity of the parameter tuning problem. We extend our study to selecting architectural hyperparameters in modern graph neural networks. We bound the Rademacher complexity for tuning the self-loop weighting in recently proposed Simplified Graph Convolution (SGC) networks. We further propose a tunable architecture that interpolates graph convolutional neural networks (GCN) and graph attention networks (GAT) in every layer, and provide Rademacher complexity bounds for tuning the interpolation coefficient.
Cite
@article{arxiv.2502.12937,
title = {Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees},
author = {Ally Yalei Du and Eric Huang and Dravyansh Sharma},
journal= {arXiv preprint arXiv:2502.12937},
year = {2025}
}
Comments
31 pages (12 pages main body), 2 figures. UAI 2025