Spectral Manifold Harmonization for Graph Imbalanced Regression
This addresses a significant lack of research in imbalanced regression for graph data, particularly in scientific domains like chemistry and drug discovery, though it appears incremental as it builds on existing methods by incorporating graph topology and targeting specific ranges.
The paper tackles imbalanced regression on graph-structured data by introducing Spectral Manifold Harmonization (SMH), which generates synthetic graph samples to focus on relevant target ranges, resulting in improved predictive performance for those ranges on chemistry and drug discovery benchmarks.
Graph-structured data is ubiquitous in scientific domains, where models often face imbalanced learning settings. In imbalanced regression, domain preferences focus on specific target value ranges that represent the most scientifically valuable cases; however, we observe a significant lack of research regarding this challenge. In this paper, we present Spectral Manifold Harmonization (SMH), a novel approach to address imbalanced regression challenges on graph-structured data by generating synthetic graph samples that preserve topological properties while focusing on the most relevant target distribution regions. Conventional methods fail in this context because they either ignore graph topology in case generation or do not target specific domain ranges, resulting in models biased toward average target values. Experimental results demonstrate the potential of SMH on chemistry and drug discovery benchmark datasets, showing consistent improvements in predictive performance for target domain ranges. Code is available at https://github.com/brendacnogueira/smh-graph-imbalance.git.