paper-with-me

Papers

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

2022-06-16 · NeurIPS 2023 11 · Hanchen Wang, Jean Kaddour, Shengchao Liu, Jian Tang, Joan Lasenby, Qi Liu

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.

📄 PDF Abstract BibTeX arXiv:2206.08005

Code (1)

hansen7/molgrapheval 공식 구현 pytorch

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction

2026-02-23 · Jiele Wu, Haozhe Ma, Zhihan Guo, Thanh Vinh Vo 외 arxiv

Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling cos…

Molecular Property PredictionSelf-Supervised LearningRepresentation LearningTransfer Learning

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining

2025-09-26 · Boshra Ariguib, Mathias Niepert, Andrei Manolache arxiv

High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on molecular graphs has shown promise, many e…

Representation LearningGraph Neural Network

Knowledge-aware Contrastive Molecular Graph Learning

2021-03-24 · Yin Fang, Haihong Yang, Xiang Zhuang, Xin Shao 외

Leveraging domain knowledge including fingerprints and functional groups in molecular representation learning is crucial for chemical property prediction and drug discovery. When modeling the relation between graph struc…

Contrastive LearningDrug DiscoveryGraph Learningmolecular representation+3

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction

2021-10-03 · NeurIPS 2021 12 · Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu 외

Predicting molecular properties with data-driven methods has drawn much attention in recent years. Particularly, Graph Neural Networks (GNNs) have demonstrated remarkable success in various molecular generation and predi…

Molecular Property PredictionProperty PredictionRetrosynthesisSelf-Supervised Learning

Large-Scale Chemical Language Representations Capture Molecular Structure and Properties

2021-06-17 · Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan, Inkit Padhi 외

Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promi…

Drug DiscoveryMolecular Property Predictionmolecular representationRepresentation Learning