GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Ruifeng, Li, Mingqian, Liu, Wei, Chen, Hongyang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929585173561344
author Li, Ruifeng
Li, Mingqian
Liu, Wei
Chen, Hongyang
author_facet Li, Ruifeng
Li, Mingqian
Liu, Wei
Chen, Hongyang
contents Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning approaches are based on Graph Neural Networks (GNNs). However, these approaches struggle with three significant challenges: insufficient annotations, molecular diversity, and architectural limitations such as over-squashing, which leads to the loss of critical structural details. To address these challenges, we introduce a new class of GNNs that integrates the Kolmogorov-Arnold Networks (KANs), known for their robust data-fitting capabilities and high accuracy in small-scale AI + Science tasks. By incorporating KANs into GNNs, our model enhances the representation of molecular structures. We further advance this approach with a variant called SwallowKAN (SKAN), which employs adaptive Radial Basis Functions (RBFs) as the core of the non-linear neurons. This innovation improves both computational efficiency and adaptability to diverse molecular structures. Building on the strengths of SKAN, we propose a new class of GNNs, GNN-SKAN, and its augmented variant, GNN-SKAN+, which incorporates a SKAN-based classifier to further boost performance. To our knowledge, this is the first work to integrate KANs into GNN architectures tailored for molecular representation learning. Experiments across 6 classification datasets, 6 regression datasets, and 4 few-shot learning datasets demonstrate that our approach achieves new state-of-the-art performance in terms of accuracy and computational cost.
format Preprint
id arxiv_https___arxiv_org_abs_2408_01018
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs
Li, Ruifeng
Li, Mingqian
Liu, Wei
Chen, Hongyang
Machine Learning
Artificial Intelligence
68T99
J.2.4
Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning approaches are based on Graph Neural Networks (GNNs). However, these approaches struggle with three significant challenges: insufficient annotations, molecular diversity, and architectural limitations such as over-squashing, which leads to the loss of critical structural details. To address these challenges, we introduce a new class of GNNs that integrates the Kolmogorov-Arnold Networks (KANs), known for their robust data-fitting capabilities and high accuracy in small-scale AI + Science tasks. By incorporating KANs into GNNs, our model enhances the representation of molecular structures. We further advance this approach with a variant called SwallowKAN (SKAN), which employs adaptive Radial Basis Functions (RBFs) as the core of the non-linear neurons. This innovation improves both computational efficiency and adaptability to diverse molecular structures. Building on the strengths of SKAN, we propose a new class of GNNs, GNN-SKAN, and its augmented variant, GNN-SKAN+, which incorporates a SKAN-based classifier to further boost performance. To our knowledge, this is the first work to integrate KANs into GNN architectures tailored for molecular representation learning. Experiments across 6 classification datasets, 6 regression datasets, and 4 few-shot learning datasets demonstrate that our approach achieves new state-of-the-art performance in terms of accuracy and computational cost.
title GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs
topic Machine Learning
Artificial Intelligence
68T99
J.2.4
url https://arxiv.org/abs/2408.01018