p–LSGR: A lightweight post–hoc latent–space resampling framework for imbalanced and complex graph distributions

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Graph neural networks (GNNs) are widely used across domains but remain sensitive to class imbalance, class overlap, and complex data distributions, limiting reliability in real-world settings. Existing imbalance-mitigation strategies provide only partial robustness, are often computationally expensive, and leave post-hoc imbalance handling largely unexplored. We propose Post-hoc Latent Space Graph Resampling (p-LSGR), a framework that exploits learned graph representations through latent-space resampling to improve minority-class learning without graph augmentation or modification of the original graph structure. Through data-aware, difficulty-aware, and ensemble-based resampling strategies, p–LSGR improves minority-class classification performance over vanilla GNNs while remaining competitive with augmentation-based approaches, with the ensemble-based variants demonstrating greater stability across encoder types. Across diverse benchmarks, p-LSGR achieves an average 42% improvement in minority-class F1 over vanilla GNNs and a 6% improvement over competing approaches while reducing processing time by up to 91%. Bayesian analysis further indicates that p-LSGR variants maintain strong minority-class performance while achieving balanced trade-offs across Minority F1, Accuracy, and AUPRC. These findings position p-LSGR as a practical and computationally efficient alternative to graph-level augmentation. We additionally release a corpus of constraint-based synthetic graph datasets derived from real electrical layouts to support research on class-imbalanced graph learning at https://data.mendeley.com/datasets/4vdpxdd7vp/1