On-device intelligence (ODI) enables artificial intelligence (AI) applications to run on end devices, providing real-time and customized AI inference without relying on remote servers. However, training models for on-device deployment face significant challenges due to the decentralized and privacy-sensitive nature of users' data, along with end-side constraints related to network connectivity, computation efficiency, etc. Existing training paradigms, such as cloud-based training, federated learning, and transfer learning, fail to sufficiently address these practical constraints that are prevalent for devices. To overcome these challenges, we propose Privacy-Enhanced Training-as-a-Service (PTaaS), a novel service computing paradigm that provides privacy-friendly, customized AI model training for end devices. PTaaS outsources the core training process to remote and powerful cloud or edge servers, efficiently developing customized on-device models based on uploaded anonymous queries, enhancing data privacy while reducing the computation load on individual devices. We explore the definition, goals, and design principles of PTaaS, alongside emerging technologies that support the PTaaS paradigm. An architectural scheme for PTaaS is also presented, followed by a series of open problems that set the stage for future research directions in the field of PTaaS.

Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in volume and diversify in classes over time. This oversight results in FL methods suffering from catastrophic forgetting, where the trained models inadvertently discard previously learned information upon assimilating new data. In response to this challenge, we propose a novel Federated Class-Incremental Learning (FCIL) method, named \underline{Fed}erated \underline{C}lass-Incremental \underline{L}earning with New-Class \underline{A}ugmented \underline{S}elf-Di\underline{S}tillation (FedCLASS). The core of FedCLASS is to enrich the class scores of historical models with new class scores predicted by current models and utilize the combined knowledge for self-distillation, enabling a more sufficient and precise knowledge transfer from historical models to current models. Theoretical analyses demonstrate that FedCLASS stands on reliable foundations, considering scores of old classes predicted by historical models as conditional probabilities in the absence of new classes, and the scores of new classes predicted by current models as the conditional probabilities of class scores derived from historical models. Empirical experiments demonstrate the superiority of FedCLASS over four baseline algorithms in reducing average forgetting rate and boosting global accuracy.

Federated Learning (FL) enables training Artificial Intelligence (AI) models over end devices without compromising their privacy. As computing tasks are increasingly performed by a combination of cloud, edge, and end devices, FL can benefit from this End-Edge-Cloud Collaboration (EECC) paradigm to achieve collaborative device-scale expansion with real-time access. Although Hierarchical Federated Learning (HFL) supports multi-tier model aggregation suitable for EECC, prior works assume the same model structure on all computing nodes, constraining the model scale by the weakest end devices. To address this issue, we propose Agglomerative Federated Learning (FedAgg), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedAgg recursively organizes computing nodes among all tiers based on Bridge Sample Based Online Distillation Protocol (BSBODP), which enables every pair of parent-child computing nodes to mutually transfer and distill knowledge extracted from generated bridge samples. This design enhances the performance by exploiting the potential of larger models, with privacy constraints of FL and flexibility requirements of EECC both satisfied. Experiments under various settings demonstrate that FedAgg outperforms state-of-the-art methods by an average of 4.53\% accuracy gains and remarkable improvements in convergence rate.