XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction

2026-01-26

AI Summary

This work addresses the challenge that existing graph neural networks often fail to outperform traditional molecular fingerprint methods in molecular property prediction under data-scarce conditions. To overcome this limitation, the authors propose Cross-graph Interactive Message Passing (XIMP), a novel framework that integrates interpretable chemical priors as inductive biases by enabling joint message propagation across multiple levels of abstraction—specifically, the molecular graph, a scaffold-aware junction tree, and a simplified pharmacophore-encoded graph. XIMP supports both direct and indirect interactions among an arbitrary number of graph abstractions and fuses their representations to enhance generalization. Evaluated on ten diverse molecular property prediction tasks, the method consistently outperforms state-of-the-art models, with particularly significant gains in low-data regimes.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate molecular property prediction is central to drug discovery, yet graph neural networks often underperform in data-scarce regimes and fail to surpass traditional fingerprints. We introduce cross-graph inter-message passing (XIMP), which performs message passing both within and across multiple related graph representations. For small molecules, we combine the molecular graph with scaffold-aware junction trees and pharmacophore-encoding extended reduced graphs, integrating complementary abstractions. While prior work is either limited to a single abstraction or non-iterative communication across graphs, XIMP supports an arbitrary number of abstractions and both direct and indirect communication between them in each layer. Across ten diverse molecular property prediction tasks, XIMP outperforms state-of-the-art baselines in most cases, leveraging interpretable abstractions as an inductive bias that guides learning toward established chemical concepts, enhancing generalization in low-data settings.

Problem

• molecular property prediction
• graph neural networks
• data-scarce regimes
• molecular representation
• drug discovery

Innovation

• cross-graph message passing
• molecular property prediction
• graph neural networks
• inductive bias
• multi-graph representation