Meta-GraphKAN:Few-Shot Graph Kolmogorov Arnold learning Networks for Molecular Property Prediction

Molecular Property Prediction (MPP) plays a crucial role in the drug discovery process. Despite numerous advancements of deep learning in this field, identifying the unknown properties of molecules remains quite challenging due to the scarcity of labeled data and the imbalance in class distribution. Furthermore, many existing methods emphasize atom-level information transfer and overlook crucial data conveyed by molecular bonds and their interrelationships. This neglect results in insufficient attention being paid to the key sub-structures within molecules, such as pharmacophores and toxophores.We propose a novel framework, Meta-GraphKAN, which combines Kolmogorov-Arnold Networks (KAN) and Graph Neural Networks (GNNs) within the meta-learning framework to address these issues. Specifically, we utilize structure reconfiguration in which "bonds" are converted into nodes and "bond-atom-bond" interactions are transformed into edges to better partition the bonds. Moreover, to capture information about the molecular structure from different perspectives, we encode the original graph and the reconfigured graph using the GraphKAN network to generate molecular embeddings. We then adopt a graph contrastive learning strategy to train on both the original and structurally reconfigured molecular graphs, resulting in the final molecular representation. Our extensive experiments validate the efficacy of the proposed method, and our method achieves state-of-the-art performance on three public datasets.