Few-Shot Graph Learning for Molecular Property Prediction

Guo, Zhu Ming; Zhang, Chuxu; Yu, Wenhao; Herr, John E.; Wiest, Olaf; Jiang, Meng; Chawla, Nitesh V.

doi:10.1145/3442381.3450112

Cited by 90 publications

(63 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models used input data in the Simplified Molecular-Input Line-Entry (SMILES) format. However, SMILES does not optimally preserve the molecular structure [31]. Thus, the first bridge works [32], [33] combined different molecular fingerprints and molecular graphs as input.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, the first bridge works [32], [33] combined different molecular fingerprints and molecular graphs as input. Recently a group of models were introduced that use the molecular graph as input [31], [34], [35]. For example, [31] suggested metalearning framework to obtain better results on a small number of samples.…”

Section: Related Workmentioning

confidence: 99%

“…Recently a group of models were introduced that use the molecular graph as input [31], [34], [35]. For example, [31] suggested metalearning framework to obtain better results on a small number of samples. Proper pooling operations are another way to improve the graph representation and to present the entire graph structure.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Mullakaeva¹,

Cosmo²,

Kazi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property prediction and brain connectome analysis. Importantly, recent works have shown that considering relationships between input data samples have a positive regularizing effect for the downstream task in healthcare applications. These relationships are naturally modeled by a (possibly unknown) graph structure between input samples. In this work, we propose Graph-in-Graph (GiG), a neural network architecture for protein classification and brain imaging applications that exploits the graph representation of the input data samples and their latent relation. We assume an initially unknown latent-graph structure between graph-valued input data and propose to learn end-to-end a parametric model for message passing within and across input graph samples, along with the latent structure connecting the input graphs. Further, we introduce a degree distribution loss that helps regularize the predicted latent relationships structure. This regularization can significantly improve the downstream task. Moreover, the obtained latent graph can represent patient population models or networks of molecule clusters, providing a level of interpretability and knowledge discovery in the input domain of particular value in healthcare.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Mullakaeva¹,

Cosmo²,

Kazi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, one of the main challenges is that molecules are heterogeneous structure where each atom has connection with different neighboring atoms via different types of bonds. Secondly, often a limited amount of data on labeled molecular property are available; and thus, to predict new molecular properties, meta-learning techniques [Guo+21] can be relevant and effective.…”

Section: Emerging Applicationsmentioning

confidence: 99%

Meta-Learning with Graph Neural Networks: Methods and Applications

Mandal¹,

Medya²,

Uzzi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems. However, GNNs on such applications are limited when there are few available samples. Meta-learning has been an important framework to address the lack of samples in machine learning, and in recent years, the researchers have started to apply meta-learning to GNNs. In this work, we provide a comprehensive survey of different meta-learning approaches involving GNNs on various graph problems showing the power of using these two approaches together. We categorize the literature based on proposed architectures, shared representations, and applications. Finally, we discuss several exciting future research directions and open problems.

show abstract

“…To alleviate the limited data problem in cheminformatics, various transfer learning 18,[72][73][74][75] and multitask learning methods [76][77][78][79][80] have been recently developed. Inspired by the success of pretraining followed by finetuning in CV and NLP, Goh et al 81 proposed ChemNet, where a deep neural network is pretrained on a large set of compounds in a self-supervised manner and then fine-tuned on individual activity/prediction tasks.…”

Section: Transfer Learning In Sar Predictionsmentioning

confidence: 99%

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Dey,

Machiraju,

Ning

2021

Preprint

View full text Add to dashboard Cite

Recent advances in molecular machine learning, especially deep neural networks such as Graph Neural Networks (GNNs) for predicting structure activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks are limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another, and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to

show abstract

Few-Shot Graph Learning for Molecular Property Prediction

Cited by 90 publications

References 34 publications

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Meta-Learning with Graph Neural Networks: Methods and Applications

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Contact Info

Product

Resources

About