MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph.
MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph.
复制标题
DOI：
10.1145/3447548.3467186
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
近年来，在生物医学领域利用图神经网络(GNN)来解决与药物有关的问题得到了迅速的发展。然而，像任何其他深层体系结构一样，GNN需要数据。虽然在现实世界中要求标签通常是昂贵的，但以无监督的方式预先训练GNN已经得到了积极的探索。其中，图对比学习通过最大化成对图扩充之间的互信息，已被证明对各种下游任务是有效的。然而，目前的图形对比学习框架有两个局限性。首先，扩充是为一般图形设计的，因此可能不适合或不够强大于某些领域。其次，对比方案只学习对局部扰动不变的表示，因此不考虑数据集的全局结构，这也可能对下游任务有用。在这篇文章中，我们研究了专门为生物医学领域设计的图对比学习，其中存在分子图。我们提出了一种新的框架，称为MoCL，它利用局部和全局的领域知识来辅助表示学习。局部级领域知识指导扩充过程，从而在不改变图语义的情况下引入变化。全局级知识对整个数据集中的图之间的相似性信息进行编码，有助于学习具有更丰富语义的表示。整个模型是通过双重对比目标来学习的。在线性和半监督环境下，我们在不同的分子数据集上对MoCL进行了评估，结果表明MoCL达到了最先进的性能。
Recent years have seen a rapid growth of utilizing graph neural networks (GNNs) in the biomedical domain for tackling drug-related problems. However, like any other deep architectures, GNNs are data hungry. While requiring labels in real world is often expensive, pretraining GNNs in an unsupervised manner has been actively explored. Among them, graph contrastive learning, by maximizing the mutual information between paired graph augmentations, has been shown to be effective on various downstream tasks. However, the current graph contrastive learning framework has two limitations. First, the augmentations are designed for general graphs and thus may not be suitable or powerful enough for certain domains. Second, the contrastive scheme only learns representations that are invariant to local perturbations and thus does not consider the global structure of the dataset, which may also be useful for downstream tasks. In this paper, we study graph contrastive learning designed specifically for the biomedical domain, where molecular graphs are present. We propose a novel framework called MoCL, which utilizes domain knowledge at both local- and global-level to assist representation learning. The local-level domain knowledge guides the augmentation process such that variation is introduced without changing graph semantics. The global-level knowledge encodes the similarity information between graphs in the entire dataset and helps to learn representations with richer semantics. The entire model is learned through a double contrast objective. We evaluate MoCL on various molecular datasets under both linear and semi-supervised settings and results show that MoCL achieves state-of-the-art performance.
登录
查看更多内容
影响因子：
7.3
作者：
Meanwell, Nicholas A.
通讯作者：
Meanwell, Nicholas A.
影响因子：
8.6
作者：
Bajusz D;Rácz A;Héberger K
通讯作者：
Héberger K
影响因子：
5.6
作者：
Rogers, David;Hahn, Mathew
通讯作者：
Hahn, Mathew
影响因子：
1.5
作者：
Leo, Enrico;Molinari, Alessandro L. C.;Lorenzi, Giovanni
通讯作者：
Lorenzi, Giovanni
影响因子：
8.6
作者：
Gayvert KM;Madhukar NS;Elemento O
通讯作者：
Elemento O