DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism
This addresses the challenge of handling inherent heterogeneity in social data for federated social event detection, which is an incremental improvement over existing federated learning paradigms.
The paper tackles the problem of training social event detection models through federated learning (FedSED) by proposing DAMe, a personalized federated learning framework with a dual aggregation mechanism, which demonstrated effectiveness in experiments using six social event datasets across six languages and two platforms and showed resistance to injection attacks.
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.