构建真实图数据噪声基准，评估GNN抗噪能力
Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark
- 设计算法与LLM模拟实例相关噪声，更贴近真实场景
- 发现LLM生成的噪声最难处理，节点特化参数能提升鲁棒性
- 适合研究图神经网络抗噪、标签清洗与鲁棒训练的学者
图神经网络（GNN）在节点分类任务中表现优异，但面对现实数据中的标签噪声时表现不佳。现有研究多依赖类别相关噪声假设，忽视了实例相关噪声的复杂性，难以反映真实数据污染模式。本文提出BeGIN（Benchmarking for Graphs with Instance-dependent Noise），一个包含多种噪声类型的真实图数据集基准，全面评估不同GNN架构、噪声检测方法及抗噪学习策略的效果。为模拟实例相关污染，BeGIN引入算法生成方法和基于大语言模型（LLM）的仿真机制。实验揭示实例相关噪声（尤其是LLM生成的噪声）带来的挑战，并强调节点级参数化对提升GNN鲁棒性的关键作用。通过系统评估，BeGIN为理解各类抗噪方法的有效性、效率及性能影响因素提供了深刻洞见。代码已开源：https://github.com/kimsu55/BeGIN。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification tasks but struggle with label noise in real-world data. Existing studies on graph learning with label noise commonly rely on class-dependent label noise, overlooking the complexities of instance-dependent noise and falling short of capturing real-world corruption patterns. We introduce BeGIN (Benchmarking for Graphs with Instance-dependent Noise), a new benchmark that provides realistic graph datasets with various noise types and comprehensively evaluates noise-handling strategies across GNN architectures, noisy label detection, and noise-robust learning. To simulate instance-dependent corruptions, BeGIN introduces algorithmic methods and LLM-based simulations. Our experiments reveal the challenges of instance-dependent noise, particularly LLM-based corruption, and underscore the importance of node-specific parameterization to enhance GNN robustness. By comprehensively evaluating noise-handling strategies, BeGIN provides insights into their effectiveness, efficiency, and key performance factors. We expect that BeGIN will serve as a valuable resource for advancing research on label noise in graphs and fostering the development of robust GNN training methods. The code is available at https://github.com/kimsu55/BeGIN.
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。