提出GRaNDe度量，提升图像分类中图神经网络的邻居重要性感知能力。
Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification
- 用高斯距离加权与排名结合，动态衡量邻居节点重要性。
- 在五个公开数据集上均实现准确率提升，优于或媲美当前最优方法。
- 适合需要精准建模节点关系的图像分类任务，尤其标注数据稀缺场景。
数据激增导致标注成本高昂，而无标签数据大量存在。图神经网络（GNN）通过利用关系结构，可同时学习标签与无标签数据，适用于半监督学习。现有方法多采用基于度的归一化，但通常假设邻居节点重要性均等。在图像分类中，图常基于特征相似性构建，若对所有邻居一视同仁，则可能忽略其重要性的差异。为此，本文提出新型度量方法GRaNDe（Gaussian Rank-based Neighborhood Degree），融合邻居排序与高斯距离加权，更精准捕捉节点重要性。在五个公开图像分类数据集上的实验表明，该方法实现了持续的准确率提升，结果优于或媲美现有最先进方法。
原文摘要 · Abstract (English)
The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural Networks (GNNs) have emerged as a promising solution, as they exploit relational structures and learn from both labeled and unlabeled data, performing semi-supervised learning. A crucial component of many of these models is degree-based normalization, which influences message propagation but typically assumes uniform importance among neighboring nodes. In image classification, graphs are usually constructed from feature similarity, where treating all neighbors equally may overlook important variations in relevance. Motivated by this gap, we propose GRaNDe (Gaussian Rank-based Neighborhood Degree). This novel degree measure integrates neighborhood ranking with Gaussian distance weighting to better capture node importance. Experiments on five public image classification datasets show consistent accuracy improvements and competitive or superior results compared to state-of-the-art methods.
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。