Oct 2025· arXiv.org· Vol abs/2510.07289· 0 citations· 68 references
Computer Science
TL;DR
Molecular graph representation learning is widely used in chemical and biomedical research, and reusing widely available and well-validated pre-trained 2D encoders, while incorporating molecular domain knowledge during downstream adaptation, offers a more practical alternative.
Abstract
Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated strong performance, they overlook the rich molecular domain knowledge associated with submolecular instances (atoms and bonds). While molecular pre-training approaches incorporate such knowledge into their pre-training objectives, they typically employ designs tailored to a specific type of knowledge, lacking the flexibility to integrate diverse knowledge present in molecules. Hence, reusing widely available and well-validated pre-trained 2D encoders, while incorporating molecular domain knowledge during downstream adaptation, offers a more practical alternative. In this work, we propose MolGA, which adapts pre-trained 2D graph encoders to downstream molecular applications by flexibly incorporating diverse molecular domain knowledge. First, we propose a molecular alignment strategy that bridge the gap between pre-trained topological representations with domain-knowledge representations. Second, we introduce a conditional adaptation mechanism that generates instance-specific tokens to enable fine-grained integration of molecular domain knowledge for downstream tasks. Finally, we conduct extensive experiments on eleven public datasets, demonstrating the effectiveness of MolGA.
This paper proposes a molecular prompting framework that integrates heterogeneous molecular information into downstream graph learning without modifying the pre-trained encoder parameters, and can be flexibly incorporated into existing 2D graph pre-training methods while maintaining strong parameter efficiency.
This work proposes Molrep-SCF, a multimodal self-supervised pretraining framework for molecular representation learning using SMILES sequences, 2D molecular graphs, and 3D geometric structures that consistently outperforms existing multi-modal frameworks on molecular property prediction and other tasks.
Meng Ma, Qing-Qing Cao, Fang Liu et al.· Frontiers in Pharmacology· 0 citations
A novel multimodal alignment framework for joint modeling of molecular graphs and sequences, called Mol-ME, which employs ensemble learning to predict on extracted representations, which captures complex nonlinear relationships and compensates for the modeling limitations of single shallow networks.
Bao-Ren Huang, Mu Chen, Jun-Jie Luo et al.· Journal of Chemical Informat...· 0 citations
LeJEPA is adapted to molecular graphs, evaluating GPS and Chemprop-style D-MPNN encoders on the antibiotic-activity dataset and ogbg-molhiv using a multi-seed, bootstrap-based protocol, and pretraining supplies complementary information best realised through feature-level combination, while finetuning gains are weak an...
Michał Kulczykowski, Rafał Łabędzki· Research Square· 0 citations
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026