Graph Collaborative Filtering (GCF) has achieved state-of-the-art performance for recommendation tasks. However, most GCF structures simplify the feature transformation and nonlinear operation during message passing in the graph convolution network (GCN). We revisit these two components and discover that a part of feature transformation and nonlinear operation during message passing in GCN can improve the representation of GCF, but increase the difficulty of training. In this work, we propose a simple and effective graph-based recommendation model called FourierKAN-GCF. Specifically, it utilizes a novel Fourier Kolmogorov-Arnold Network (KAN) to replace the multilayer perceptron (MLP) as a part of the feature transformation during message passing in GCN, which improves the representation power of GCF and is easy to train. We further employ message dropout and node dropout strategies to improve the representation power and robustness of the model. Extensive experiments on two public datasets demonstrate the superiority of FourierKAN-GCF over most state-of-the-art methods. The implementation code is available at https://github.com/Jinfeng-Xu/FKAN-GCF.

翻译：图协同过滤（GCF）在推荐任务中已取得最先进的性能。然而，大多数GCF结构简化了图卷积网络（GCN）中消息传递过程中的特征变换和非线性操作。我们重新审视了这两个组成部分，发现GCN中消息传递过程中的部分特征变换和非线性操作可以提升GCF的表示能力，但会增加训练难度。在本工作中，我们提出了一种简单有效的基于图的推荐模型，称为傅里叶KAN-GCF。具体而言，它利用一种新颖的傅里叶柯尔莫哥洛夫-阿诺德网络（KAN）来替代多层感知机（MLP），作为GCN中消息传递过程中的部分特征变换，从而提升了GCF的表示能力且易于训练。我们进一步采用了消息丢弃和节点丢弃策略来提升模型的表示能力和鲁棒性。在两个公开数据集上的大量实验证明了傅里叶KAN-GCF相较于大多数最先进方法的优越性。实现代码可在 https://github.com/Jinfeng-Xu/FKAN-GCF 获取。