M-GLC: Motif-Driven Global-Local Context Graphs for Few-shot Molecular Property Prediction

2025-10-23

AI Summary

Few-shot molecular property prediction (FSMPP) suffers from reliance on large-scale labeled data in conventional methods and insufficient guidance from existing graph-structure modeling approaches. Method: This paper proposes a chemically motivated global–local contextual graph framework, constructing a tripartite heterogeneous graph linking molecules, chemical substructures, and properties to explicitly incorporate domain-specific chemical priors. It introduces a global tripartite graph propagation mechanism for cross-task knowledge transfer and integrates local subgraph attention encoding to emphasize task-critical structural motifs. Contribution/Results: Evaluated on five standard FSMPP benchmarks, the method consistently outperforms state-of-the-art approaches, demonstrating the effectiveness and robustness of synergistically optimizing global semantic associations with fine-grained local structural modeling.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Local Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Molecular property prediction (MPP) is a cornerstone of drug discovery and materials science, yet conventional deep learning approaches depend on large labeled datasets that are often unavailable. Few-shot Molecular property prediction (FSMPP) addresses this scarcity by incorporating relational inductive bias through a context graph that links molecule nodes to property nodes, but such molecule-property graphs offer limited structural guidance. We propose a comprehensive solution: Motif Driven Global-Local Context Graph for few-shot molecular property prediction, which enriches contextual information at both the global and local levels. At the global level, chemically meaningful motif nodes representing shared substructures, such as rings or functional groups, are introduced to form a global tri-partite heterogeneous graph, yielding motif-molecule-property connections that capture long-range compositional patterns and enable knowledge transfer among molecules with common motifs. At the local level, we build a subgraph for each node in the molecule-property pair and encode them separately to concentrate the model's attention on the most informative neighboring molecules and motifs. Experiments on five standard FSMPP benchmarks demonstrate that our framework consistently outperforms state-of-the-art methods. These results underscore the effectiveness of integrating global motif knowledge with fine-grained local context to advance robust few-shot molecular property prediction.

Problem

• Addresses few-shot molecular property prediction with limited labeled data
• Enhances structural guidance using global motif-molecule-property connections
• Integrates local context graphs to focus on informative neighboring molecules

Innovation

• Introduces motif nodes for global tri-partite graph structure
• Builds local subgraphs to focus on informative neighbors
• Integrates global motif knowledge with local context encoding