arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.03320cs.LG
收藏

BioBridge:通过知识图谱桥接生物医学基础模型

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Amazon AWS AI(亚马逊AWS人工智能部门);Amazon Search(亚马逊搜索部门)

Zifeng Wang, Zichen Wang, Balasubramaniam Srinivasan, Vassilis N. Ioannidis, Huzefa Rangwala, Rishita Anubhai

AI总结:

本文提出参数高效框架 BioBridge,利用知识图谱在不微调单模态生物医学基础模型的情况下学习模态间转换,在跨模态检索、域外泛化、问答和药物生成中表现优异。

摘要:

基础模型(FMs)能够利用大量未标记数据,在广泛任务中展现出卓越性能。然而,为生物医学领域开发的基础模型在很大程度上仍停留在单模态阶段,即被独立训练并分别用于仅涉及蛋白质序列、仅涉及小分子结构或仅涉及临床数据的任务。为克服生物医学基础模型的这一局限,我们提出 BioBridge,这是一种新颖的参数高效学习框架,用于桥接独立训练的单模态基础模型,以建立多模态行为。BioBridge 通过利用知识图谱(KG)学习一个单模态基础模型与另一个单模态基础模型之间的转换来实现这一目标,且不会微调任何底层单模态基础模型。我们的实验结果表明,在跨模态检索任务中,BioBridge 能够优于最佳基线知识图谱嵌入方法(平均提升约 76.3%)。我们还发现,BioBridge 通过外推至未见过的模态或关系,展现出域外泛化能力。此外,我们还表明,BioBridge 可作为通用检索器,既能够辅助生物医学多模态问答,也能够增强新型药物的引导生成。

英文摘要:

Foundation models (FMs) are able to leverage large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small molecule structures alone, or clinical data alone. To overcome this limitation of biomedical FMs, we present BioBridge, a novel parameter-efficient learning framework, to bridge independently trained unimodal FMs to establish multimodal behavior. BioBridge achieves it by utilizing Knowledge Graphs (KG) to learn transformations between one unimodal FM and another without fine-tuning any underlying unimodal FMs. Our empirical results demonstrate that BioBridge can beat the best baseline KG embedding methods (on average by around 76.3%) in cross-modal retrieval tasks. We also identify BioBridge demonstrates out-of-domain generalization ability by extrapolating to unseen modalities or relations. Additionally, we also show that BioBridge presents itself as a general purpose retriever that can aid biomedical multimodal question answering as well as enhance the guided generation of novel drugs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑