arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.08209cs.LG
收藏

GIPA:一种通用的图学习信息传播算法

GIPA: A General Information Propagation Algorithm for Graph Learning

Fudan University(复旦大学);Alibaba Group(阿里巴巴集团);Zhejiang University(浙江大学);Link2Do Technology(Link2Do科技);Tsinghua University(清华大学);Guangzhou University(广州大学)

Houyi Li, Zhihong Chen, Zhao Li, Qinkai Zheng, Peng Zhang, Shuigeng Zhou

摘要:

图神经网络(GNN)已广泛用于图结构数据计算,在诸如节点分类、链接预测和网络推荐的各种应用中显示出有前途的性能。现有的工作主要集中在节点之间的相关性进行加权聚合的邻居节点的注意力的基础上,如点积的两个节点的密集向量。这可能导致在进行信息传播时传播节点中的冲突噪声。为了解决这个问题,我们提出了一个通用的信息传播算法(简称GIPA),它利用更细粒度的信息融合,包括逐位和逐特征的相关性的基础上边缘特征在其传播。具体而言,逐位相关基于节点及其边的密集表示,通过多层感知器(MLP)计算逐元素注意力权重;逐特征相关基于节点属性特征的独热表示,用于特征选择。我们评估了GIPA在开放图基准蛋白质(OGBN蛋白质)数据集和阿里巴巴支付宝数据集上的性能。实验结果表明,GIPA在预测精度方面优于最先进的模型,例如,GIPA实现了$0.8901\pm 0.0011$的平均ROC-AUC,优于OGBN-蛋白排行榜中列出的所有现有方法。

英文摘要:

Graph neural networks (GNNs) have been widely used in graph-structured data computation, showing promising performance in various applications such as node classification, link prediction, and network recommendation. Existing works mainly focus on node-wise correlation when doing weighted aggregation of neighboring nodes based on attention, such as dot product by the dense vectors of two nodes. This may cause conflicting noise in nodes to be propagated when doing information propagation. To solve this problem, we propose a General Information Propagation Algorithm (GIPA in short), which exploits more fine-grained information fusion including bit-wise and feature-wise correlations based on edge features in their propagation. Specifically, the bit-wise correlation calculates the element-wise attention weight through a multi-layer perceptron (MLP) based on the dense representations of two nodes and their edge; The feature-wise correlation is based on the one-hot representations of node attribute features for feature selection. We evaluate the performance of GIPA on the Open Graph Benchmark proteins (OGBN-proteins for short) dataset and the Alipay dataset of Alibaba. Experimental results reveal that GIPA outperforms the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average ROC-AUC of $0.8901\pm 0.0011$, which is better than that of all the existing methods listed in the OGBN-proteins leaderboard.

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。

↑