# LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation Source: [LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:22:26.639Z Authors: Rui Xue, Haoyu Han, MohamadAli Torkamani, Jian Pei, Xiaorui Liu Published: 2023-02-03T02:33:07.000Z ## Abstract Recent works have demonstrated the benefits of capturing long-distance dependency in graphs by deeper graph neural networks (GNNs). But deeper GNNs suffer from the long-lasting scalability challenge due to the neighborhood explosion problem in large-scale graphs. In this work, we propose to capture long-distance dependency in graphs by shallower models instead of deeper models, which leads to a much more efficient model, LazyGNN, for graph representation learning. Moreover, we demonstrate that LazyGNN is compatible with existing scalable approaches (such as sampling methods) for further accelerations through the development of mini-batch LazyGNN. Comprehensive experiments demonstrate its superior prediction performance and scalability on large-scale benchmarks. The implementation of LazyGNN is available at https://github.com/RXPHD/Lazy\_GNN. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Node Classification on ogbn-products (Micro-F1, Macro-F1)](): Node Classification; OGBN-Products; Micro F1 Score: 77.6. - [Node Classification on ogbn-arxiv (Micro/Macro F1)](): Node Classification; Ogbn-arxiv; Micro F1 Score: 71.63. - [Node Classification on ogbn-paper100M](): Node Classification; ogbn-paper100M; Micro-F1: 61.97. ## Original sources and implementation [Original paper]() [PDF]()