Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters
This work addresses scalability issues in graph learning for practitioners by providing theoretical validation for mini-batch learning on graphs.
The paper tackles the problem of graph classification under partial observation by developing a theoretical framework for learning from randomly sampled subgraphs, resulting in new generalization bounds and size-generalizability without input assumptions.
Theoretical analyses for graph learning methods often assume a complete observation of the input graph. Such an assumption might not be useful for handling any-size graphs due to the scalability issues in practice. In this work, we develop a theoretical framework for graph classification problems in the partial observation setting (i.e., subgraph samplings). Equipped with insights from graph limit theory, we propose a new graph classification model that works on a randomly sampled subgraph and a novel topology to characterize the representability of the model. Our theoretical framework contributes a theoretical validation of mini-batch learning on graphs and leads to new learning-theoretic results on generalization bounds as well as size-generalizability without assumptions on the input.