Influence Propagation for Linear Threshold Model with Graph Neural Networks
Influence Propagation for Linear Threshold Model with Graph Neural Networks
复制标题
DOI：
10.1109/icdmw60847.2023.00149
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Francisco Santos;Anna Stephens;Pang-Ning Tan;A. Esfahanian
中科院分区：
文献类型：
--
作者：
Francisco Santos;Anna Stephens;Pang-Ning Tan;A. Esfahanian
影响传播是一种控制信息在网络中如何扩散的网络现象。随着深度学习的出现，人们越来越感兴趣的是应用图神经网络来提取节点的显著特征表示，用于各种网络挖掘任务，如预测信息级联的病毒性。鉴于社会影响的重要性，本文提出了一种名为IP-GNN的新型深度学习框架，用于模拟复杂网络中的信息传播过程，并学习在线性阈值模型下嵌入有关扩散过程信息的节点表示。我们的框架采用带有自适应扩散核的改进图卷积网络架构来捕获信息的远程传播，以及熵正则化的损失函数混合，以确保准确的预测和更快的学习算法收敛。在4个真实数据集上的实验结果表明，该模型准确地模拟了线性阈值模型的输出，在所有数据集上实现了超过90%的平均准确率。
Influence propagation is a network phenomenon governing how information is diffused in a network. With the advent of deep learning, there has been growing interest in applying graph neural networks to extract salient feature representation of the nodes for a variety of network mining tasks, such as forecasting the virality of information cascade. Given the importance of social influence, this paper presents a novel deep learning framework called IP-GNN for simulating the information propagation process in a complex network and learning a node representation that embeds information about the diffusion process under the linear threshold model. Our framework employs a modified graph convolutional network architecture with adaptive diffusion kernel to capture long-range propagation of information along with an entropy-regularized mixture of loss functions to ensure accurate prediction and faster convergence of the learning algorithm. Experimental results on 4 real-world datasets show that the model accurately mimics the output of the linear threshold model, achieving an average accuracy that exceeds 90% on all datasets.