Accurate protein function prediction is fundamental to advancing drug discovery and precision medicine and understanding complex biological systems. Although Gene Ontology (GO) provides a standardized framework for protein annotation, a critical challenge persists: the imbalance between low-specificity GO terms and high-specificity GO terms. This imbalance creates blind spots in our understanding of protein function landscapes, particularly in clinically relevant pathways. Here, we present ProGO-PSL, a novel large graph architecture designed to resolve this imbalance. ProGO-PSL simultaneously leverages explicit domain identifiers from InterPro and implicit evolutionary contexts from multiple sequence alignments, fusing these complementary data sources within a powerful imbalance learning framework. Our model consistently outperforms state-of-the-art methods by 5%–15% across all specificity levels and on both a benchmark data set and an independent test set, demonstrating robust generalization. Furthermore, ProGO-PSL generates interpretable representations that clarify relationships between low- and high-specificity GO terms, enabling a more complete functional characterization of the proteome. This work accelerates the identification of therapeutic targets in previously uncharacterized biological pathways.