aiqbench analysis
HiFi-Mol advances molecular property prediction by integrating hierarchical graph encoders with contextualized fingerprint embeddings, addressing the limitations of single-view pretraining methods. This multi-view framework demonstrates a measurable 2.77% improvement in ROC-AUC on scaffold split benchmarks, offering a robust approach for generalizing to structurally novel compounds with limited labeled data. The work represents a significant step forward in applying advanced machine learning techniques to accelerate drug discovery and chemical informatics.
Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints
arXiv:2609.15611v1 Announce Type: cross Abstract: Molecular property prediction requires representations that generalize from limited labeled data to structurally novel compounds. Existing molecular pretraining methods often rely on a single view: graph-based approaches model atom-bond topology but provide limited fragment-level supervision, whereas fingerprint descriptors encode chemical patterns but are typically used as fixed auxiliary features. We propose HiFi-Mol, a multi-view framework that separately pretrains a hierarchical graph encoder and a contextualized fingerprint encoder before downstream integration. The graph branch uses fragment-aware masking with multi-resolution supervision to capture substructure-aware representations, while the fingerprint branch tokenizes active entries from seven fingerprint families and applies masked language modeling to learn contextualized embeddings. During fine-tuning, HiFi-Mol combines projected multi-resolution graph features with fingerprint embeddings for downstream prediction. Evaluated on MoleculeNet benchmarks under the scaffold split, HiFi-Mol achieves a 2.77% improvement in average ROC-AUC over the best baseline across eight classification tasks while maintaining competitive performance on three regression tasks. Further analyses reveal that fragment-aware masking improves graph representation quality, and classification results demonstrate dataset-dependent strengths of the individual graph and fingerprint variants, confirming that the two views provide complementary predictive signals.
Abstract:Molecular property prediction requires representations that generalize from limited labeled data to structurally novel compounds. Existing molecular pretraining methods often rely on a single view: graph-based approaches model atom-bond topology but provide limited fragment-level supervision, whereas fingerprint descriptors encode chemical patterns but are typically used as fixed auxiliary features. We propose HiFi-Mol, a multi-view framework that separately pretrains a hierarchical graph encoder and a contextualized fingerprint encoder before downstream integration. The graph branch uses fragment-aware masking with multi-resolution supervision to capture substructure-aware representations, while the fingerprint branch tokenizes active entries from seven fingerprint families and applies masked language modeling to learn contextualized embeddings. During fine-tuning, HiFi-Mol combines projected multi-resolution graph features with fingerprint embeddings for downstream prediction. Evaluated on MoleculeNet benchmarks under the scaffold split, HiFi-Mol achieves a 2.77% improvement in average ROC-AUC over the best baseline across eight classification tasks while maintaining competitive performance on three regression tasks. Further analyses reveal that fragment-aware masking improves graph representation quality, and classification results demonstrate dataset-dependent strengths of the individual graph and fingerprint variants, confirming that the two views provide complementary predictive signals.
The paper has been accepted as a Full Research Paper at CIKM '26. Source code is available at this https URL
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.15611 [cs.LG]
(or arXiv:2609.15611v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.15611 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 299 words
Related coverage
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · Jul 15, 2026
When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning
arXiv · Sep 16, 2026
MoTIF-X: A Multimodal Tokenized Framework for Interpretable and Extensible Molecular Representation Learning
arXiv · Sep 30, 2026
HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
arXiv · Sep 3, 2026