Geometric Matrix Completion via Sylvester Multi-Graph Neural Network
Geometric Matrix Completion via Sylvester Multi-Graph Neural Network
复制标题
DOI：
10.1145/3583780.3615170
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Boxin Du;Changhe Yuan;Fei Wang;Hanghang Tong
中科院分区：
文献类型：
--
作者：
Boxin Du;Changhe Yuan;Fei Wang;Hanghang Tong
尽管Sylvester方程赋权方法在半监督标签学习和网络对齐等各种图挖掘应用中取得了成功，但仍然存在一些局限性。西尔维斯特方程不能对非线性关系进行建模，不能针对不同的任务进行调整，这限制了它的性能。本文提出了一种端到端神经网络框架SYMGNN，该框架由多网络神经聚合模块和先验多网络联想融合学习模块组成。该框架继承了西尔维斯特方程的核心思想，同时推广了西尔维斯特方程以克服上述局限性。在真实数据集上的实验评估表明，SYMGNN的实例化在几何矩阵完成任务中的整体表现优于基线，其低阶实例化可以进一步平均减少16.98%的内存消耗。
Despite the success of the Sylvester equation empowered methods on various graph mining applications, such as semi-supervised label learning and network alignment, there also exists several limitations. The Sylvester equation's inability of modeling non-linear relations and the inflexibility of tuning towards different tasks restrict its performance. In this paper, we propose an end-to-end neural framework, SYMGNN, which consists of a multi-network neural aggregation module and a prior multi-network association incorporation learning module. The proposed framework inherits the key ideas of the Sylvester equation, and meanwhile generalizes it to overcome aforementioned limitations. Empirical evaluations on real-world datasets show that the instantiations of SYMGNN overall outperform the baselines in geometric matrix completion task, and its low-rank instantiation could further reduce the memory consumption by 16.98% on average.