MOBICOM

Personalized federated learning aims to address two key challenges in federated systems: performance degradation of the global model, and the lack of specificity to individual clients. Both of them are caused by client heterogeneity. Previous solutions ...

In contrast to federated learning, collaborative learning aims to reduce data transfer caused by frequent model updates by creating lightweight tailored models at the edge nodes. If the model needs to adapt due to environmental changes such as drift in ...

Federated learning (FL) has yielded impressive results in recent years. However, its effectiveness on non-independently and identically distributed (non-i.i.d) data remains challenging. Existing work aims to address this challenge through client ...

The edge network has been introduced for providing computing capabilities to accelerate federated learning. However, the heterogeneity of edge networks increases the complexity of traffic scheduling, which can result in network congestion and decreased ...

Adversarial robustness received significant attention over the past years, due to its critical practical role. Complementary to the existing literature on adversarial training, we explore weight-space ensembles of independently trained models. We propose ...