轻量级图网络高效捕捉长程依赖，性能超越主流模型
GraphMinNet: Learning Dependencies in Graphs with Light Complexity Minimal Architecture
- 用最小化门控单元思想构建轻量图网络，线性复杂度建模长距离关系
- 在10个数据集上6项领先，分子与图像图任务表现优异
- 理论保证梯度不衰减，适合需全局结构理解的任务
图神经网络在诸多应用中表现卓越，但难以有效捕捉长程依赖。本文提出GraphMinNet，将最小化门控循环单元的思想推广至图结构数据。该方法以线性计算复杂度实现高效的长程依赖建模，同时保持置换等变性和稳定性。通过融合特征编码与位置编码，模型结合了结构与位置信息，理论上表达能力强于1-WL测试。理论分析表明，GraphMinNet可实现长距离无衰减梯度传播。在包括分子图、图像图和合成网络在内的10个多样化数据集上进行的大量实验显示，GraphMinNet在6个数据集上达到最优性能，其余表现也具竞争力，验证了其对局部与全局图结构的有效建模能力。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have demonstrated remarkable success in various applications, yet they often struggle to capture long-range dependencies (LRD) effectively. This paper introduces GraphMinNet, a novel GNN architecture that generalizes the idea of minimal Gated Recurrent Units to graph-structured data. Our approach achieves efficient LRD modeling with linear computational complexity while maintaining permutation equivariance and stability. The model incorporates both structural and positional information through a unique combination of feature and positional encodings, leading to provably stronger expressiveness than the 1-WL test. Theoretical analysis establishes that GraphMinNet maintains non-decaying gradients over long distances, ensuring effective long-range information propagation. Extensive experiments on ten diverse datasets, including molecular graphs, image graphs, and synthetic networks, demonstrate that GraphMinNet achieves state-of-the-art performance while being computationally efficient. Our results show superior performance on 6 out of 10 datasets and competitive results on the others, validating the effectiveness of our approach in capturing both local and global graph structures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。