DAMe:具有双重聚合机制的个性化联邦社交事件检测
DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism
AI总结:
本文提出个性化联邦社交事件检测框架DAMe,通过贝叶斯优化的局部聚合、全局聚合及事件中心约束解决数据异构与客户端漂移问题,并在多语言多平台数据上验证其有效性和抗攻击鲁棒性。
摘要:
通过联邦学习训练社交事件检测模型(FedSED)旨在提升参与者在任务上的表现。然而,现有联邦学习范式不足以实现FedSED的目标,并且在处理社交数据固有的异构性方面存在局限。本文提出了一种用于社交事件检测的、具有双重聚合机制的个性化联邦学习框架,即DAMe。我们提出了一种新颖的局部聚合策略,利用贝叶斯优化在保留局部特征的同时融入全局知识。此外,我们引入了一种全局聚合策略,为客户端的偏好提供最大程度的外部知识。另外,我们引入了一个全局-局部事件中心约束,以防止局部过拟合和“客户端漂移”。在自然联邦设置的真实模拟中,利用涵盖六种语言和两个社交媒体平台的六个社交事件数据集进行的实验以及消融研究,证明了所提框架的有效性。进一步的鲁棒性分析表明,DAMe对注入攻击具有抵抗力。
英文摘要:
Training social event detection models through federated learning (FedSED) aims to improve participants' performance on the task. However, existing federated learning paradigms are inadequate for achieving FedSED's objective and exhibit limitations in handling the inherent heterogeneity in social data. This paper proposes a personalized federated learning framework with a dual aggregation mechanism for social event detection, namely DAMe. We present a novel local aggregation strategy utilizing Bayesian optimization to incorporate global knowledge while retaining local characteristics. Moreover, we introduce a global aggregation strategy to provide clients with maximum external knowledge of their preferences. In addition, we incorporate a global-local event-centric constraint to prevent local overfitting and ``client-drift''. Experiments within a realistic simulation of a natural federated setting, utilizing six social event datasets spanning six languages and two social media platforms, along with an ablation study, have demonstrated the effectiveness of the proposed framework. Further robustness analyses have shown that DAMe is resistant to injection attacks.
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。