Drug-drug interaction (DDI) prediction is central to drug discovery and clinical development, particularly in the context of increasingly prevalent polypharmacy. Although existing computational methods achieve strong performance on standard benchmarks, they often fail to generalize to realistic deployment scenarios, where most candidate drug pairs involve previously unseen drugs and validated interactions are scarce. We demonstrate that proximity in the embedding spaces of prevailing molecule-centric DDI models does not reliably correspond to interaction labels, and that simply scaling up model capacity therefore fails to improve generalization. To address these limitations, we propose GenRel-DDI, a generalizable relation learning framework that reformulates DDI prediction as a relation-centric learning problem, in which interaction representations are learned independently of drug identities. This relation-level abstraction enables the capture of transferable interaction patterns that generalize to unseen drugs and novel drug pairs. Extensive experiments across multiple benchmark demonstrate that GenRel-DDI consistently and significantly outperforms state-of-the-art methods, with particularly large gains on strict entity-disjoint evaluations, highlighting the effectiveness and practical utility of relation learning for robust DDI prediction. The code is available at https://github.com/SZU-ADDG/GenRel-DDI.

翻译：药物相互作用（DDI）预测是药物发现和临床开发的核心环节，尤其是在日益普遍的多药治疗背景下。尽管现有计算方法在标准基准测试中取得了优异性能，但它们往往难以泛化到真实的部署场景中，因为大多数候选药物对都涉及先前未见的药物，且经过验证的相互作用十分稀缺。我们证明，当前以分子为中心的DDI模型在其嵌入空间中的邻近性并不能可靠地对应于相互作用标签，因此单纯扩大模型容量并不能改善泛化能力。为解决这些局限性，我们提出了GenRel-DDI，一个可泛化的关系学习框架，它将DDI预测重新表述为一个以关系为中心的学习问题，其中相互作用的表示学习独立于药物身份。这种关系层面的抽象能够捕获可迁移的相互作用模式，从而泛化到未见过的药物和新的药物对。在多个基准测试上进行的大量实验表明，GenRel-DDI始终显著优于最先进的方法，尤其是在严格的实体不相交评估中取得了特别大的性能提升，这凸显了关系学习对于稳健DDI预测的有效性和实际效用。代码可在 https://github.com/SZU-ADDG/GenRel-DDI 获取。