With the recent success of graph convolutional networks (GCNs), they have been widely applied for recommendation, and achieved impressive performance gains. The core of GCNs lies in its message passing mechanism to aggregate neighborhood information. However, we observed that message passing largely slows down the convergence of GCNs during training, especially for large-scale recommender systems, which hinders their wide adoption. LightGCN makes an early attempt to simplify GCNs for collaborative filtering by omitting feature transformations and nonlinear activations. In this paper, we take one step further to propose an ultra-simplified formulation of GCNs (dubbed UltraGCN), which skips infinite layers of message passing for efficient recommendation. Instead of explicit message passing, UltraGCN resorts to directly approximate the limit of infinite-layer graph convolutions via a constraint loss. Meanwhile, UltraGCN allows for more appropriate edge weight assignments and flexible adjustment of the relative importances among different types of relationships. This finally yields a simple yet effective UltraGCN model, which is easy to implement and efficient to train. Experimental results on four benchmark datasets show that UltraGCN not only outperforms the state-of-the-art GCN models but also achieves more than 10x speedup over LightGCN. Our source code will be available at https://reczoo.github.io/UltraGCN.

翻译：随着图卷积网络（GCNs）的最新成功，它们已被广泛用于推荐系统，并取得了显著的性能提升。GCNs的核心在于其通过消息传递机制聚合邻域信息。然而，我们观察到消息传递在很大程度上降低了GCNs在训练过程中的收敛速度，尤其是在大规模推荐系统中，这阻碍了它们的广泛采用。LightGCN通过省略特征变换和非线性激活，对简化用于协同过滤的GCNs进行了初步尝试。在本文中，我们进一步提出了一种超简化的GCNs公式（称为UltraGCN），它跳过了无限层的消息传递以实现高效推荐。UltraGCN不进行显式的消息传递，而是通过约束损失直接近似无限层图卷积的极限。同时，UltraGCN允许更合适的边权重分配以及灵活调整不同类型关系之间的相对重要性。最终，这产生了一个简单而有效的UltraGCN模型，易于实现且训练高效。在四个基准数据集上的实验结果表明，UltraGCN不仅优于最先进的GCN模型，而且相比LightGCN实现了超过10倍的加速。我们的源代码将在https://reczoo.github.io/UltraGCN上提供。