Topology-Aware Active Learning on Graphs

TL;DR

This paper introduces a topology-aware active learning framework on graphs that uses curvature-based methods for efficient exploration and exploitation, improving label efficiency in classification tasks.

Contribution

It presents a novel curvature-based coreset construction and dynamic exploration-exploitation switching strategy for active learning on graphs.

Findings

Outperforms existing semi-supervised baselines at low label rates.

Uses curvature-based methods for better exploration and exploitation.

Incorporates multiscale information through localized graph rewiring.

Abstract

We propose a graph-topological approach to active learning that directly targets the core challenge of exploration versus exploitation under scarce label budgets. To guide exploration, we introduce a coreset construction algorithm based on Balanced Forman Curvature (BFC), which selects representative initial labels that reflect the graph's cluster structure. This method includes a data-driven stopping criterion that signals when the graph has been sufficiently explored. We further use BFC to dynamically trigger the shift from exploration to exploitation within active learning routines, replacing hand-tuned heuristics. To improve exploitation, we introduce a localized graph rewiring strategy that efficiently incorporates multiscale information around labeled nodes, enhancing label propagation while preserving sparsity. Experiments on benchmark classification tasks show that our methods consistently outperform existing graph-based semi-supervised baselines at low label rates.