arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.08005cs.LGq-bio.QM
收藏

评估分子图嵌入的自监督学习

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

Cambridge(剑桥大学);UCL(伦敦大学学院);MILA(米拉人工智能研究所);UdeM(蒙特利尔大学);HEC(巴黎高等商学院);CIFAR(加拿大高等研究院);HKU(香港大学)

Hanchen Wang, Jean Kaddour, Shengchao Liu, Jian Tang, Joan Lasenby, Qi Liu

AI总结:

本文提出分子图表示评估基准MOLGRAPHEVAL,通过通用图、分子子结构和嵌入空间属性三类探测任务评估GSSL方法,发现现有数据集评估与细致探测结果存在显著不一致,表明当前评估方法不全面。

摘要:

图自监督学习(GSSL)提供了一种无需专家标注即可获取嵌入的稳健途径,由于潜在分子数量庞大且获取标签成本高昂,这一能力对分子图具有深远影响。然而,GSSL方法并非针对特定领域内的优化而设计,而是为了在多种下游任务中实现可迁移性。这种广泛的适用性使其评估变得复杂。为应对这一挑战,我们提出了“分子图表示评估”(MOLGRAPHEVAL),通过可解释且多样化的任务生成分子图嵌入的详细剖析。MOLGRAPHEVAL提供了一组探测任务,分为三个类别:(i) 通用图,(ii) 分子子结构,以及(iii) 嵌入空间属性。通过利用MOLGRAPHEVAL将现有GSSL方法在现有下游数据集和我们的任务集上进行基准测试,我们发现仅从现有数据集得出的推断与从更细致的探测得出的推断之间存在显著不一致。这些发现表明,当前的评估方法未能捕捉整个图景。

英文摘要:

Graph Self-Supervised Learning (GSSL) provides a robust pathway for acquiring embeddings without expert labelling, a capability that carries profound implications for molecular graphs due to the staggering number of potential molecules and the high cost of obtaining labels. However, GSSL methods are designed not for optimisation within a specific domain but rather for transferability across a variety of downstream tasks. This broad applicability complicates their evaluation. Addressing this challenge, we present "Molecular Graph Representation Evaluation" (MOLGRAPHEVAL), generating detailed profiles of molecular graph embeddings with interpretable and diversified attributes. MOLGRAPHEVAL offers a suite of probing tasks grouped into three categories: (i) generic graph, (ii) molecular substructure, and (iii) embedding space properties. By leveraging MOLGRAPHEVAL to benchmark existing GSSL methods against both current downstream datasets and our suite of tasks, we uncover significant inconsistencies between inferences drawn solely from existing datasets and those derived from more nuanced probing. These findings suggest that current evaluation methodologies fail to capture the entirety of the landscape.

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。

↑