arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.04493cs.LGcs.AI
收藏

图特征选通网络

Graph Feature Gating Networks

Michigan State University(密歇根州立大学);Vanderbilt University(范德堡大学);IBM T. J. Watson Research Center(IBM托马斯·J·沃森研究中心)

Wei Jin, Xiaorui Liu, Yao Ma, Tyler Derr, Charu Aggarwal, Jiliang Tang

摘要:

图神经网络(GNN)由于其在学习有效的图表示方面的能力而受到极大的关注。大多数GNN遵循消息传递方案,其中通过聚合和转换来自邻域的信息来更新节点表示。同时,它们对不同特征维的信息采用相同的聚合策略。然而,根据社会维度理论和谱嵌入的建议,在聚合过程中对维度进行不同的处理有潜在的好处。在这项工作中,我们研究了GNN中特征维度的异质贡献。特别是,我们提出了一个通用的图形特征门控网络(GFGN)的基础上的图形信号去噪问题,然后相应地引入三个图形滤波器下GFGN允许不同水平的贡献,从特征尺寸。在各种真实数据集上的大量实验证明了所提出的框架的有效性和鲁棒性。

英文摘要:

Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs. Most GNNs follow a message-passing scheme where the node representations are updated by aggregating and transforming the information from the neighborhood. Meanwhile, they adopt the same strategy in aggregating the information from different feature dimensions. However, suggested by social dimension theory and spectral embedding, there are potential benefits to treat the dimensions differently during the aggregation process. In this work, we investigate to enable heterogeneous contributions of feature dimensions in GNNs. In particular, we propose a general graph feature gating network (GFGN) based on the graph signal denoising problem and then correspondingly introduce three graph filters under GFGN to allow different levels of contributions from feature dimensions. Extensive experiments on various real-world datasets demonstrate the effectiveness and robustness of the proposed frameworks.

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。

↑