Shi Yong, Quan Pei, Xiao Yang, Lei Minglong, Niu Lingfeng
IEEE Trans Cybern. 2023 Oct;53(10):6146-6159. doi: 10.1109/TCYB.2022.3164474. Epub 2023 Sep 15.
Due to the extraordinary abilities in extracting complex patterns, graph neural networks (GNNs) have demonstrated strong performances and received increasing attention in recent years. Despite their prominent achievements, recent GNNs do not pay enough attention to discriminate nodes when determining the information sources. Some of them select information sources from all or part of neighbors without distinction, and others merely distinguish nodes according to either graph structures or node features. To solve this problem, we propose the concept of the Influence Set and design a novel general GNN framework called the graph influence network (GINN), which discriminates neighbors by evaluating their influences on targets. In GINN, both topological structures and node features of the graph are utilized to find the most influential nodes. More specifically, given a target node, we first construct its influence set from the corresponding neighbors based on the local graph structure. To this aim, the pairwise influence comparison relations are extracted from the paths and a HodgeRank-based algorithm with analytical expression is devised to estimate the neighbors' structure influences. Then, after determining the influence set, the feature influences of nodes in the set are measured by the attention mechanism, and some task-irrelevant ones are further dislodged. Finally, only neighbor nodes that have high accessibility in structure and strong task relevance in features are chosen as the information sources. Extensive experiments on several datasets demonstrate that our model achieves state-of-the-art performances over several baselines and prove the effectiveness of discriminating neighbors in graph representation learning.
由于在提取复杂模式方面具有非凡能力，图神经网络（GNN）近年来展现出强大性能并受到越来越多关注。尽管取得了显著成就，但近期的GNN在确定信息源时对区分节点的关注不足。其中一些无差别地从所有或部分邻居中选择信息源，另一些则仅根据图结构或节点特征来区分节点。为解决此问题，我们提出影响集的概念并设计了一种名为图影响网络（GINN）的新型通用GNN框架，该框架通过评估邻居对目标的影响来区分邻居。在GINN中，图的拓扑结构和节点特征都被用于找到最具影响力的节点。更具体地说，给定一个目标节点，我们首先基于局部图结构从相应邻居中构建其影响集。为此，从路径中提取成对影响比较关系，并设计一种具有解析表达式的基于霍奇秩的算法来估计邻居的结构影响。然后，在确定影响集之后，通过注意力机制测量集合中节点的特征影响，并进一步排除一些与任务无关的节点。最后，仅选择在结构上具有高可达性且在特征上具有强任务相关性的邻居节点作为信息源。在多个数据集上进行的大量实验表明，我们的模型在多个基线之上实现了当前最优性能，并证明了在图表示学习中区分邻居的有效性。
