为每个节点定制最佳层数，提升图神经网络分类精度。
Personalized Layer Selection for Graph Neural Networks
- 为每个节点选择最优表示层，基于与类别原型的距离判断。
- 在10个数据集上显著提升分类准确率，效果可即插即用。
- 使模型更深层且抗攻击能力增强，适合追求高精度的场景。
图神经网络（GNN）通常对节点周围的局部结构进行固定粒度的特征聚合以预测标签。然而，不同节点可能依赖于其邻域的不同粒度来反映节点级属性，统一使用单一层级的平滑处理会对分类产生负面影响。本文挑战了单一GNN层适用于所有节点的传统假设，提出为每个节点训练专属的个性化层级。受度量学习启发，我们设计MetSelect1算法：在变换后的GNN层中识别每类的原型表示，并在该层中通过归一化方差后计算节点到原型的最小距离进行分类。在10个数据集和3种不同GNN架构上的实验表明，该方法显著提升了节点分类性能，且支持即插即用。此外，动态选择层可使模型更深，同时增强对投毒攻击的鲁棒性。本工作希望推动未来研究向更自适应、个性化的图表示学习发展。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact that a single GNN layer can classify all nodes of a graph by training GNNs with a distinct personalized layer for each node. Inspired by metric learning, we propose a novel algorithm, MetSelect1, to select the optimal representation layer to classify each node. In particular, we identify a prototype representation of each class in a transformed GNN layer and then, classify using the layer where the distance is smallest to a class prototype after normalizing with that layer's variance. Results on 10 datasets and 3 different GNNs show that we significantly improve the node classification accuracy of GNNs in a plug-and-play manner. We also find that using variable layers for prediction enables GNNs to be deeper and more robust to poisoning attacks. We hope this work can inspire future works to learn more adaptive and personalized graph representations.
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。