Model Agnostic Graph Prompt Learning for Crystal Property Prediction
2026-07-09 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors propose a new method to help Graph Neural Networks (GNNs) better predict properties of crystals without needing extra expert knowledge. They add special 'soft prompts' that capture hidden important features both at the level of individual atoms and the whole crystal structure. This approach improves the prediction accuracy of existing GNN models by 3% to 15% on standard datasets. Additionally, the soft prompts allow knowledge to be shared between different property predictions, which is especially useful when training data is limited.
Graph Neural NetworksCrystal Property PredictionSoft Prompt LearningNode-level FeaturesGraph-level FeaturesChemical SemanticsStructural SymmetryKnowledge TransferMachine LearningMaterial Science
Authors
Shrimon Mukherjee, Kishalay Das, Partha Basuchowdhuri, Pawan Goyal, Niloy Ganguly
Abstract
Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties. These models often encode domain-specific knowledge into their graph encoding modules, which increases their parameter size and makes their performance heavily dependent on domain expertise. Added to this, explicitly incorporating all chemical and structural features, that might influence a specific crystal property into the GNN encoder, is a challenging task. In this work, we propose a soft prompt learning framework that captures latent features essential for property prediction, which are not explicitly provided to the GNN. We introduce a novel multilevel graph prompt learning framework comprising both node-level and graph-level soft prompts. At the node level, we capture the local chemical semantics of different atom types, while at the graph level, we encode the global structural symmetry of the crystal graph. Our proposed prompt learning framework is lightweight and seamlessly integrates with any existing GNN encoder. Extensive experiments on popular benchmark datasets show that incorporating prompt learning significantly improves (3\% - 15\%) the performance of state-of-the-art GNN models in crystal property prediction tasks. Furthermore, the learned soft prompts enable cross-property knowledge transfer, enhancing prediction performance for properties with limited training data. Code is available at https://github.com/shrimonmuke0202/Prompt.git