[论文解读] Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach

Changjun Fan, Li Zeng+4 more|arXiv (Cornell University)|May 24, 2019

Complex Network Analysis Techniques参考文献 41被引用 18

一句话总结

该论文提出了一种新颖的图神经网络模型 DeepRanker for BC，通过在小型网络上进行训练并推广至大型网络，学习识别高介数中心性（BC）节点。该模型采用编码器-解码器框架，结合邻域聚合与多层感知机解码，其推理速度比当前最先进的近似方法快达数百至数千倍，同时在排名前几位高BC节点时保持或超越其准确性。

ABSTRACT

Betweenness centrality (BC) is one of the most used centrality measures for network analysis, which seeks to describe the importance of nodes in a network in terms of the fraction of shortest paths that pass through them. It is key to many valuable applications, including community detection and network dismantling. Computing BC scores on large networks is computationally challenging due to high time complexity. Many approximation algorithms have been proposed to speed up the estimation of BC, which are mainly sampling-based. However, these methods are still prone to considerable execution time on large-scale networks, and their results are often exacerbated when small changes happen to the network structures. In this paper, we focus on identifying nodes with high BC in a graph, since many application scenarios are built upon retrieving nodes with top-k BC. Different from previous heuristic methods, we turn this task into a learning problem and design an encoder-decoder based framework to resolve the problem. More specifcally, the encoder leverages the network structure to encode each node into an embedding vector, which captures the important structural information of the node. The decoder transforms the embedding vector for each node into a scalar, which captures the relative rank of this node in terms of BC. We use the pairwise ranking loss to train the model to identify the orders of nodes regarding their BC. By training on small-scale networks, the learned model is capable of assigning relative BC scores to nodes for any unseen networks, and thus identifying the highly-ranked nodes. Comprehensive experiments on both synthetic and real-world networks demonstrate that, compared to representative baselines, our model drastically speeds up the prediction without noticeable sacrifce in accuracy, and outperforms the state-of-the-art by accuracy on several large real-world networks.

研究动机与目标

• 解决在包含数百万个节点的大规模网络上精确计算介数中心性的计算不可行性问题。
• 减少对依赖采样、对网络扰动敏感的慢速近似算法的依赖。
• 将识别 top-k 高BC 节点的问题转化为使用图神经网络的端到端学习排序问题。
• 开发一种归纳式模型，可在不同类型的网络之间泛化，并高效扩展至未见过的大规模网络。
• 与现有基线方法相比，在显著降低推理时间的同时，实现高精度的 top-k BC 节点排序。

提出的方法

• 该模型采用编码器-解码器架构：编码器使用邻域聚合图神经网络生成捕捉节点与介数中心性结构相关性的节点嵌入。
• 解码器为多层感知机，将每个节点嵌入映射为表示节点相对 BC 重要性的标量排序分数。
• 模型通过成对排序损失进行端到端训练，以保留节点真实 BC 值之间的相对顺序。
• 训练在小型合成网络（如幂律聚类、ER、BA 模型）上进行，从而实现向更大规模真实世界图的泛化。
• 编码器模仿 Brandes 算法的结构聚合模式，与 BC 计算的内在逻辑保持一致。
• 该模型为归纳式模型，意味着其可对训练过程中未见过的图进行预测，从而适用于大规模动态网络的部署。

实验结果

研究问题

• RQ1 图神经网络能否在不计算精确 BC 值的情况下，有效学习预测节点按介数中心性的相对排序？
• RQ2 在小型合成网络上训练的模型，在识别大型真实世界网络中的 top-BC 节点时，泛化能力如何？
• RQ3 训练图分布的选择（如 PL-cluster、ER、BA）在多大程度上影响模型的泛化性能？
• RQ4 学习到的排序模型能否在 top-k BC 节点识别任务中，同时实现比现有采样近似算法更高的速度和准确性？
• RQ5 哪些架构和训练选择使得模型能在极低计算成本下实现高性能？

主要发现

• 所提出的模型在推理速度上比 KADABRA 和 ABRA 快达 1000 倍，且在 top-1% 和 top-5% 节点排序中保持相当或更优的准确性。
• 在五种真实世界网络中的三种中，该模型在 top-1% 和 top-5% 准确率上达到最高，甚至在排序保真度上超越了精确算法。
• 在所有数据集上，该模型与真实 BC 排名的 Kendall tau 距离始终最低，表明其排序质量更优。
• 在幂律聚类（PL-cluster）合成图上进行训练，可在多种真实世界网络类型中实现最佳泛化性能。
• 该模型在包含数百万个节点的网络上仍保持高准确性，展现出强大的可扩展性与归纳偏差。
• 与对拓扑变化敏感的采样方法不同，该模型对网络扰动具有鲁棒性。