基于强化联邦图神经网络的个性化公共安全突发事件检测方法

近年来,将公共安全数据转换为图的形式,通过图神经网络构造节点表示应用于下游任务的方法,充分利用了公共安全数据的实体与关联信息,取得了较好的效果.为了提高模型的有效性,需要大量的高质量数据,但是高质量的数据通常归属于政府、公司和组织,很难通过数据集中的方式使模型学习到有效的事件检测模型.由于各数据拥有方的关注主题与收集时间不同,数据之间存在Non-IID的问题.传统的假设一个全局模型可以适合所有客户端的方法难以解决此类问题.本文提出了基于强化联邦图神经网络的公共安全突发事件检测方法PPSED,各客户端采用多方协作的方式训练个性化的模型来解决本地的突发事件检测任务.设计联邦公共安全突发事件检测模型的本地训练与梯度量化模块,采用基于图采样的minibatch机制的GraphSage构造公共安全突发事件检测本地模型,以减小数据Non-IID的影响,采用梯度量化方法减小梯度通信的消耗.设计基于随机图嵌入的客户端状态感知模块,在保护隐私的同时更好地保留客户端模型有价值的梯度信息.设计强化联邦图神经网络的个性化梯度聚合与量化策略,采用DDPG拟合个性化联邦学习梯度聚合加权策略,并根据权重决定是否对梯度进行量化,对模型的性能与通信压力进行平衡.通过在微博平台收集的公共安全数据集和三个公开的图数据集进行了大量的实验,实验结果表明了提出的方法的有效性.

Personalized Public Safety Event Detection Method based on Reinforcement Federated Graph Neural Network

In recent years, the method of transforming public safety data into graph form and constructing node representations through graph neural networks for training and inference of downstream tasks has fully exploited the entity and association information of public safety data, achieving excellent results. However, to enhance the effectiveness of the model, a large amount of high-quality data is needed, which is usually held by governments, companies, and organizations, making it difficult to learn an effective event detection model through data centralization. Moreover, due to different focuses and collection times of the data from various parties, there is a Non-IID (Independent and Identically Distributed) problem among the data. Traditional methods that assume a global model can accommodate all clients are challenging to solve such issues. Therefore, this paper proposes a personalized public safety emergency event detection (PPSED) method based on a Reinforcement Federated Graph Neural Network. In this method, each client trains a personalized and more robust model through multi-party collaboration to solve local emergency detection tasks. We designed a local training and gradient quantization module for the federated public safety emergency event detection model and trained GraphSage through a minibatch mechanism based on graph sampling to construct a local model for public safety emergency detection. This approach reduces the impact of Non-IID data and supports the gradient quantization method to lower the consumption of gradient communication. We also designed a client state awareness module based on random graph embedding, which better retains the valuable information of the client model while protecting privacy. Furthermore, we designed a personalized gradient aggregation and quantization strategy for the federated graph neural network. We used Deep Deterministic Policy Gradient (DDPG) to fit a personalized federated learning gradient aggregation weighting strategy, and determined whether the gradient can be quantized based on the weight, balancing the model''s performance and communication pressure. This study demonstrated the effectiveness of the method through extensive experiments on a public safety dataset collected from the Weibo platform and three public graph datasets.