Accurately characterizing friction behaviors at water–solid interfaces remains a challenge because of the dynamic nature of water molecules and temporal variations in solid surface charges. By using a density-functional-theory (DFT) based machine learning (ML) technique and long-time ML-parametrized molecular dynamics simulations, we have systematically investigated water-induced charge polarization and redistribution on graphene, as well as its impact on friction at water-graphene interfaces. Heterogeneous charge polarization and distribution are observed for water-covered graphene accompanied by the formation of electric double layers (EDLs). The introduction of defects into graphene significantly enhances the heterogeneity in charge polarization and distribution. Compared to pristine graphene, defected graphene exhibits reduced friction at water-graphene interfaces due to stronger charge heterogeneity, resulting in lower surface charge density and the inverse relationship between slip length and surface charge density for EDLs. Our results highlight the pivotal roles of defects and charge heterogeneity in reducing friction at water-graphene interfaces.