Understanding compound-protein interactions is crucial for early drug discovery, offering insights into molecular mechanisms and potential therapeutic effects of compounds. Here, we introduce GraphBAN, a graph-based framework that inductively predicts these interactions using compound and protein feature information. GraphBAN effectively handles inductive link predictions for unseen nodes, providing a robust solution for predicting interactions between entirely unseen compounds and proteins. This capability enables GraphBAN to transcend the constraints of traditional methods that are typically limited to known contexts. GraphBAN employs a knowledge distillation architecture through a teacher-student learning model. The teacher block leverages network structure information, while the student block focuses on node attributes, enhancing learning and prediction accuracy. Additionally, GraphBAN incorporates a domain adaptation module, increasing its effectiveness across different dataset domains. Empirical tests on five benchmark datasets demonstrate that GraphBAN outperforms ten baseline models, while a case study analysis with the Pin1 protein further supports the model's effectiveness in real world scenarios, making it as a promising tool for early drug discovery.