MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction

Yeyun Chen, Jiangming Shi
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72228-72243, 2025.

Abstract

The progress in materials science and drug discovery is impeded by the availability of labeled data and the high costs of manual annotation, driving the need for efficient strategies to capture molecular representations and enable accurate predictions. Pretrained Graph Neural Networks have shown promise in capturing universal molecular representations, but adapting them to task-specific applications remains challenging. In this paper, we propose Multilevel Informed Prompt-Tuning (MIPT), a novel framework for effectively tailoring pretrained models to molecule-related tasks. MIPT utilizes a lightweight, multi-level prompt learning module to capture node-level and graph-level task-specific knowledge, ensuring adaptable and efficient tuning. Additionally, a noise penalty mechanism is introduced to address mismatches between pretrained representations and downstream tasks, reducing irrelevant or noisy information. Experimental results show that MIPT surpasses all baselines, aligning graph space and task space while achieving significant improvements in molecule-related tasks, demonstrating its scalability and versatility for molecular tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-chen25cu, title = {{MIPT}: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction}, author = {Chen, Yeyun and Shi, Jiangming}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {72228--72243}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/chen25cu/chen25cu.pdf}, url = {https://proceedings.mlr.press/v267/chen25cu.html}, abstract = {The progress in materials science and drug discovery is impeded by the availability of labeled data and the high costs of manual annotation, driving the need for efficient strategies to capture molecular representations and enable accurate predictions. Pretrained Graph Neural Networks have shown promise in capturing universal molecular representations, but adapting them to task-specific applications remains challenging. In this paper, we propose Multilevel Informed Prompt-Tuning (MIPT), a novel framework for effectively tailoring pretrained models to molecule-related tasks. MIPT utilizes a lightweight, multi-level prompt learning module to capture node-level and graph-level task-specific knowledge, ensuring adaptable and efficient tuning. Additionally, a noise penalty mechanism is introduced to address mismatches between pretrained representations and downstream tasks, reducing irrelevant or noisy information. Experimental results show that MIPT surpasses all baselines, aligning graph space and task space while achieving significant improvements in molecule-related tasks, demonstrating its scalability and versatility for molecular tasks.} }
Endnote
%0 Conference Paper %T MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction %A Yeyun Chen %A Jiangming Shi %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-chen25cu %I PMLR %P 72228--72243 %U https://proceedings.mlr.press/v267/chen25cu.html %V 267 %X The progress in materials science and drug discovery is impeded by the availability of labeled data and the high costs of manual annotation, driving the need for efficient strategies to capture molecular representations and enable accurate predictions. Pretrained Graph Neural Networks have shown promise in capturing universal molecular representations, but adapting them to task-specific applications remains challenging. In this paper, we propose Multilevel Informed Prompt-Tuning (MIPT), a novel framework for effectively tailoring pretrained models to molecule-related tasks. MIPT utilizes a lightweight, multi-level prompt learning module to capture node-level and graph-level task-specific knowledge, ensuring adaptable and efficient tuning. Additionally, a noise penalty mechanism is introduced to address mismatches between pretrained representations and downstream tasks, reducing irrelevant or noisy information. Experimental results show that MIPT surpasses all baselines, aligning graph space and task space while achieving significant improvements in molecule-related tasks, demonstrating its scalability and versatility for molecular tasks.
APA
Chen, Y. & Shi, J.. (2025). MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:72228-72243 Available from https://proceedings.mlr.press/v267/chen25cu.html.

Related Material