Cold Brew：提取具有不完整或缺失邻域的图节点表示
Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
摘要：
图神经网络（GNN）在节点分类、回归和推荐任务中已经实现了最先进的性能。GNN在丰富和高质量的连接可用时工作良好。然而，他们的有效性往往是危及许多现实世界中的节点度有幂律分布的图。这种情况的极端情况，即节点可能没有邻居，称为严格冷启动（SCS）。SCS强制预测完全依赖于节点自身的特征。我们提出了Cold Brew，这是一种师生蒸馏方法，用于解决GNN的SCS和噪声邻居挑战。我们还引入了特征贡献率（FCR），这是一个量化归纳GNN解决SCS的行为的度量。我们的实验表明，FCR解开不同的图形数据组件的贡献，并帮助选择最佳的体系结构SCS推广。我们进一步证明了Cold Brew在几个公共基准和专有电子商务数据集上的卓越性能，其中许多节点的连接很少或有噪声。我们的源代码可在https://github.com/amazon-research/gnn-tail-generalization上获得。
英文摘要：
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification, regression, and recommendation tasks. GNNs work well when rich and high-quality connections are available. However, their effectiveness is often jeopardized in many real-world graphs in which node degrees have power-law distributions. The extreme case of this situation, where a node may have no neighbors, is called Strict Cold Start (SCS). SCS forces the prediction to rely completely on the node's own features. We propose Cold Brew, a teacher-student distillation approach to address the SCS and noisy-neighbor challenges for GNNs. We also introduce feature contribution ratio (FCR), a metric to quantify the behavior of inductive GNNs to solve SCS. We experimentally show that FCR disentangles the contributions of different graph data components and helps select the best architecture for SCS generalization. We further demonstrate the superior performance of Cold Brew on several public benchmark and proprietary e-commerce datasets, where many nodes have either very few or noisy connections. Our source code is available at https://github.com/amazon-research/gnn-tail-generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
