Complex brain networks are increasingly characterized at different scales, including global summary statistics, community connectivity, and individual edges. While research relating brain networks to demographic and behavioral measurements has yielded many insights into brain-phenotype relationships, common analytical approaches only consider network information at a single scale, thus failing to incorporate rich information present at other scales. Here, we designed, implemented, and deployed Multi-Scale Network Regression (MSNR), a penalized multivariate approach for modeling brain networks that explicitly respects both edge- and community-level information by assuming a low rank and sparse structure, both encouraging less complex and more interpretable modeling. Capitalizing on a large neuroimaging cohort (n=1,051), we demonstrate that MSNR recapitulates interpretable and statistically significant association between functional connectivity patterns with brain development, sex differences, and motion-related artifacts. Notably, compared to single-scale methods, MSNR achieves a balance between prediction performance and model complexity, with improved interpretability. Together, by jointly exploiting both edge- and community-level information, MSNR has the potential to yield novel insights into brain-behavior relationships.