arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01594cs.LGstat.ML
收藏

用于属性图嵌入的自适应图编码器

Adaptive Graph Encoder for Attributed Graph Embedding

Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学)

Ganqu Cui, Jie Zhou, Cheng Yang, Zhiyuan Liu

摘要:

属性图嵌入是从图的拓扑结构和节点特征中学习向量表示,是图分析的一个具有挑战性的任务。最近,基于图卷积网络(GCN)的方法在这方面取得了很大的进展。然而,现有的基于GCN的方法有三个主要缺点。首先,我们的实验表明,图卷积滤波器和权重矩阵的纠缠会损害性能和鲁棒性。其次,我们表明,在这些方法中的图卷积滤波器揭示了广义拉普拉斯平滑滤波器的特殊情况下,但他们不保持最佳的低通特性。最后,现有算法的训练目标通常是恢复邻接矩阵或特征矩阵,这与实际应用并不总是一致的。为了解决这些问题,我们提出了自适应图编码器(AGE),一种新的属性图嵌入框架。AGE由两个模块组成:(1)为了更好地消除节点特征中的高频噪声,AGE首先应用精心设计的拉普拉斯平滑滤波器。(2)AGE采用自适应编码器,迭代地增强过滤后的特征,以获得更好的节点嵌入。我们使用四个公共基准数据集进行实验,以验证AGE的节点聚类和链接预测任务。实验结果表明,AGE始终优于国家的最先进的图嵌入方法在这些任务上相当。

英文摘要:

Attributed graph embedding, which learns vector representations from graph topology and node features, is a challenging task for graph analysis. Recently, methods based on graph convolutional networks (GCNs) have made great progress on this task. However,existing GCN-based methods have three major drawbacks. Firstly,our experiments indicate that the entanglement of graph convolutional filters and weight matrices will harm both the performance and robustness. Secondly, we show that graph convolutional filters in these methods reveal to be special cases of generalized Laplacian smoothing filters, but they do not preserve optimal low-pass characteristics. Finally, the training objectives of existing algorithms are usually recovering the adjacency matrix or feature matrix, which are not always consistent with real-world applications. To address these issues, we propose Adaptive Graph Encoder (AGE), a novel attributed graph embedding framework. AGE consists of two modules: (1) To better alleviate the high-frequency noises in the node features, AGE first applies a carefully-designed Laplacian smoothing filter. (2) AGE employs an adaptive encoder that iteratively strengthens the filtered features for better node embeddings. We conduct experiments using four public benchmark datasets to validate AGE on node clustering and link prediction tasks. Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.

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。

↑