LGAIMNNov 2, 2024

Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction

arXiv:2411.01158v16 citationsh-index: 42NIPS
Originality Incremental advance
AI Analysis

This addresses data scarcity in drug discovery and material science, but is incremental as it builds on existing pre-trained encoders and context-aware classifiers.

The paper tackled the problem of ineffective fine-tuning in few-shot molecular property prediction by proposing Pin-Tuning, a parameter-efficient in-context tuning method that improves predictive performance with fewer trainable parameters on public datasets.

Molecular property prediction (MPP) is integral to drug discovery and material science, but often faces the challenge of data scarcity in real-world scenarios. Addressing this, few-shot molecular property prediction (FSMPP) has been developed. Unlike other few-shot tasks, FSMPP typically employs a pre-trained molecular encoder and a context-aware classifier, benefiting from molecular pre-training and molecular context information. Despite these advancements, existing methods struggle with the ineffective fine-tuning of pre-trained encoders. We attribute this issue to the imbalance between the abundance of tunable parameters and the scarcity of labeled molecules, and the lack of contextual perceptiveness in the encoders. To overcome this hurdle, we propose a parameter-efficient in-context tuning method, named Pin-Tuning. Specifically, we propose a lightweight adapter for pre-trained message passing layers (MP-Adapter) and Bayesian weight consolidation for pre-trained atom/bond embedding layers (Emb-BWC), to achieve parameter-efficient tuning while preventing over-fitting and catastrophic forgetting. Additionally, we enhance the MP-Adapters with contextual perceptiveness. This innovation allows for in-context tuning of the pre-trained encoder, thereby improving its adaptability for specific FSMPP tasks. When evaluated on public datasets, our method demonstrates superior tuning with fewer trainable parameters, improving few-shot predictive performance.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes