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 2403.08333cs.LGcs.AI
收藏

基于移除的节点影响力的快速推断

Fast Inference of Removal-Based Node Influence

University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

Weikai Li, Zhiping Xiao, Xiao Luo, Yizhou Sun

AI总结:

提出基于节点移除的快速GNN推断方法NORA,利用梯度信息仅需一次前向和反向传播即可高效近似所有节点的影响力分数,并在多数据集和模型上验证了有效性。

摘要:

图神经网络(GNNs)被广泛用于捕捉图中的信息传播模式。尽管已取得显著性能,但评估节点影响力正成为一个新的热门话题。我们提出了一种评估节点影响力的新方法,该方法通过测量移除某个节点所导致的已训练GNN模型预测变化来进行评估。一个现实应用是:“在预测Twitter账户极性的任务中,如果移除某个特定账户,其他账户的极性会如何变化?”。我们将GNN作为代理模型,其预测可以模拟由节点移除引起的节点或边的变化。我们的目标是为每个节点获取影响力分数,一种直接的方法是交替移除每个节点,并将已训练的GNN应用于修改后的图以生成新的预测。这种方法可靠但耗时,因此我们需要一种高效的方法。相关的研究工作,如图对抗攻击和反事实解释,无法直接满足我们的需求,因为它们的问题设置不同。我们提出了一种高效、直观且有效的方法,即基于节点移除的快速GNN推断(NORA),该方法使用梯度信息来近似节点移除的影响力。它仅需一次前向传播和一次反向传播即可近似所有节点的影响力分数。在六个数据集和六个GNN模型上的大量实验验证了NORA的有效性。我们的代码可在https://github.com/weikai-li/NORA.git获取。

英文摘要:

Graph neural networks (GNNs) are widely utilized to capture the information spreading patterns in graphs. While remarkable performance has been achieved, there is a new trending topic of evaluating node influence. We propose a new method of evaluating node influence, which measures the prediction change of a trained GNN model caused by removing a node. A real-world application is, "In the task of predicting Twitter accounts' polarity, had a particular account been removed, how would others' polarity change?". We use the GNN as a surrogate model whose prediction could simulate the change of nodes or edges caused by node removal. Our target is to obtain the influence score for every node, and a straightforward way is to alternately remove every node and apply the trained GNN on the modified graph to generate new predictions. It is reliable but time-consuming, so we need an efficient method. The related lines of work, such as graph adversarial attack and counterfactual explanation, cannot directly satisfy our needs, since their problem settings are different. We propose an efficient, intuitive, and effective method, NOde-Removal-based fAst GNN inference (NORA), which uses the gradient information to approximate the node-removal influence. It only costs one forward propagation and one backpropagation to approximate the influence score for all nodes. Extensive experiments on six datasets and six GNN models verify the effectiveness of NORA. Our code is available at https://github.com/weikai-li/NORA.git.

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。

↑