粒子竞争与合作用于标签噪声下鲁棒图卷积网络学习
Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise
浏览论文内容
中文总结 AI 辅助
针对GCN对标签噪声敏感的问题，提出PCC+GCN混合框架，利用粒子竞争与合作进行标签精炼，在多个噪声场景下提升准确率并降低计算开销。
中文摘要 AI 辅助
图卷积网络（GCN）对标签噪声高度敏感，因为被污染的监督信息会通过图结构传播，从而降低学习到的节点表示质量。本文提出PCC+GCN，一种混合框架，在GCN训练之前使用粒子竞争与合作（PCC）作为基于图的标签精炼阶段。PCC通过粒子支配动力学识别可疑的标记节点，并决定在GCN训练前应保留、移除或重新分配其标签。该框架还允许PCC使用的图通过基于特征的$k$近邻边进行增强，而GCN本身则在原始图结构和节点特征上进行训练。所提出的方法在NoisyGL基准的十个图数据集上进行了评估，涵盖了常规的均匀、成对和随机标签噪声，以及实例依赖的标签噪声。此外，还在Cora、CiteSeer和PubMed上进行了详细的超参数分析。在常规噪声下，PCC+GCN在评估方法中取得了最高的总体平均准确率和最佳平均排名，在干净设置和所有噪声场景下，相比基线GCN平均提升了1.67个百分点。在实例依赖噪声下，PCC+GCN与性能最佳的鲁棒方法保持竞争力，同时执行时间大幅降低，在十个数据集中的八个上是最快的鲁棒方法。结果表明，基于PCC的标签精炼为在噪声监督下提高GCN鲁棒性提供了一种有效且计算高效的预处理策略。
英文摘要
Graph Convolutional Networks (GCNs) are highly sensitive to label noise, since corrupted supervision can propagate through the graph and degrade learned node representations. This work proposes PCC+GCN, a hybrid framework that uses Particle Competition and Cooperation (PCC) as a graph-based label-refinement stage before GCN training. PCC identifies suspicious labeled nodes through particle domination dynamics and determines whether their labels should be preserved, removed, or reassigned before GCN training. The framework also allows the graph used by PCC to be augmented with feature-based $k$-nearest-neighbor edges, while the GCN itself is trained on the original graph structure and node features. The proposed method was evaluated on ten graph datasets from the NoisyGL benchmark under conventional Uniform, Pair, and Random label noise, as well as under instance-dependent label noise. A detailed hyperparameter analysis was also conducted on Cora, CiteSeer, and PubMed. Under conventional noise, PCC+GCN achieved the highest overall average accuracy and the best average rank among the evaluated methods, with an average gain of $1.67$ percentage points over the baseline GCN across the clean setting and all noisy scenarios. Under instance-dependent noise, PCC+GCN remained competitive with the best-performing robust methods while requiring substantially lower execution time, being the fastest robust method on eight of the ten datasets. The results indicate that PCC-based label refinement provides an effective and computationally efficient preprocessing strategy for improving GCN robustness under noisy supervision.
发表机构
- São Paulo State University - UNESP（圣保罗州立大学）
机构由 AI 辅助整理，请以论文原文为准。
