GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks
This addresses feature extraction limitations in graph-based applications, but appears incremental as it adapts an existing method (KANs) to a new domain (GNNs).
The paper tackles the problem of information loss in graph neural networks (GNNs) caused by multi-layer perceptrons (MLPs) and fixed activation functions, by proposing GraphKAN which replaces these with Kolmogorov Arnold Networks (KANs) for feature extraction, resulting in demonstrated effectiveness in experiments.
Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despite groundbreaking performances, we argue that Multi-layer perceptrons (MLPs) and fixed activation functions impede the feature extraction due to information loss. Inspired by Kolmogorov Arnold Networks (KANs), we make the first attempt to GNNs with KANs. We discard MLPs and activation functions, and instead used KANs for feature extraction. Experiments demonstrate the effectiveness of GraphKAN, emphasizing the potential of KANs as a powerful tool. Code is available at https://github.com/Ryanfzhang/GraphKan.