通过规范节点表示的范数一致性，提升图神经网络在不平衡和分布偏移下的分类性能。
NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency
- 强制节点嵌入范数一致，缓解邻居信息不平衡与噪声影响
- 在不平衡比0.1下，F1分数提升1.4%-25.9%；分布偏移下准确率提升1.4%-3.1%
- 方法简单有效，满足Lipschitz连续性，适合鲁棒性要求高的图学习任务
在半监督节点分类中，聚合邻域信息虽能提升图神经网络（GNN）性能，但也使其易受邻居节点不平衡或含噪的影响，进而削弱模型在分布外情况下的泛化能力。本文发现，保持节点表示的范数一致性可显著缓解上述问题。为此提出名为NodeReg的正则化优化方法，通过约束节点嵌入范数的一致性实现稳定优化。该方法简单有效，满足Lipschitz连续性，显著提升在不平衡与分布偏移场景下的性能。实验表明，在不平衡比为0.1时，基于GCN的模型在五个公开数据集上，F1分数相较最优基线提升1.4%-25.9%；在分布偏移场景下，准确率提升1.4%-3.1%。
原文摘要 · Abstract (English)
Aggregating information from neighboring nodes benefits graph neural networks (GNNs) in semi-supervised node classification tasks. Nevertheless, this mechanism also renders nodes susceptible to the influence of their neighbors. For instance, this will occur when the neighboring nodes are imbalanced or the neighboring nodes contain noise, which can even affect the GNN's ability to generalize out of distribution. We find that ensuring the consistency of the norm for node representations can significantly reduce the impact of these two issues on GNNs. To this end, we propose a regularized optimization method called NodeReg that enforces the consistency of node representation norms. This method is simple but effective and satisfies Lipschitz continuity, thus facilitating stable optimization and significantly improving semi-supervised node classification performance under the above two scenarios. To illustrate, in the imbalance scenario, when training a GCN with an imbalance ratio of 0.1, NodeReg outperforms the most competitive baselines by 1.4%-25.9% in F1 score across five public datasets. Similarly, in the distribution shift scenario, NodeReg outperforms the most competitive baseline by 1.4%-3.1% in accuracy.
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。