# ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion Source: [ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion]() Collection index: [llms.txt]() Data updated: 2026-03-11T05:00:11.798Z Authors: Xiang Li, Jianpeng Qi, Haobing Liu, Yuan Cao, Guoqing Chao, Zhongying Zhao, Junyu Dong, Xinwang Liu, Yanwei Yu Published: 2025-04-22T14:05:11.000Z ## Abstract Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, on large-scale real-world graphs, GNNs face two major challenges: (1) GNNs struggle to ensure scalability and efficiency as repeated aggregation of large neighborhoods incurs significant computational overhead; (2) GNNs suffer from over-smoothing, where excessive propagation makes node representations indistinguishable, hindering model expressiveness. To tackle these, we propose ScaleGNN, which adaptively fuses multi-hop node features for scalable and effective graph learning. We first compute per-hop pure-neighbor matrices to isolate exclusive structural signals, then apply lightweight fusion to balance low- and high-order information, preserving both local detail and global correlations. To curb redundancy and over-smoothing, we introduce Local Contribution Score (LCS)-based masking to prune low-relevance high-order neighbors, and impose learnable sparsity to selectively integrate valuable multi-hop features. Extensive experiments on real-world datasets show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency. ## 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: 81.82. - [Node Classification on ogbn-paper100M](): Node Classification; ogbn-paper100M; Micro-F1: 65.69. - [Node Classification on ogbn-arxiv (Micro/Macro F1)](): Node Classification; Ogbn-arxiv; Micro F1 Score: 73.25. - [Node Classification on General Graph Dataset](): Node Classification; General Graph Dataset; Training Time Complexity: 2. ## Original sources and implementation [Original paper]() [PDF]()