XIMP通过跨图消息传递提升小分子属性预测，尤其在数据少时表现更优。
XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction
- 融合分子图、骨架树和药效团图，多抽象间迭代通信
- 在10个任务中多数优于现有模型，低数据下性能提升显著
- 利用可解释抽象作为先验知识，适合药物发现场景
准确的分子属性预测对药物发现至关重要，但图神经网络在数据稀缺情况下表现不佳，且常不如传统指纹方法。我们提出跨图间消息传递（XIMP），在多个相关图表示之间进行内部与跨图的消息传递。针对小分子，将分子图、基于骨架感知的连接树以及编码药效团的扩展简化图相结合，整合互补的抽象表征。相比以往仅限单一抽象或非迭代通信的方法，XIMP支持任意数量的抽象，并在每层实现直接与间接通信。在十个不同的分子属性预测任务中，XIMP在多数情况下超越了最先进基线，在低数据环境下通过可解释的抽象作为归纳偏置，引导学习向已知化学概念靠拢，从而提升泛化能力。
原文摘要 · Abstract (English)
Accurate molecular property prediction is central to drug discovery, yet graph neural networks often underperform in data-scarce regimes and fail to surpass traditional fingerprints. We introduce cross-graph inter-message passing (XIMP), which performs message passing both within and across multiple related graph representations. For small molecules, we combine the molecular graph with scaffold-aware junction trees and pharmacophore-encoding extended reduced graphs, integrating complementary abstractions. While prior work is either limited to a single abstraction or non-iterative communication across graphs, XIMP supports an arbitrary number of abstractions and both direct and indirect communication between them in each layer. Across ten diverse molecular property prediction tasks, XIMP outperforms state-of-the-art baselines in most cases, leveraging interpretable abstractions as an inductive bias that guides learning toward established chemical concepts, enhancing generalization in low-data settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。