Federated Continual Learning through distillation in pervasive computing
Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more general model. Current solutions rely on the availability of large amounts of stored data at the client side in order to fine-tune the models sent by the server. Such setting is not realistic in mobile pervasive computing where data storage must be kept low and data characteristic can change dramatically. To account for this variability, a solution is to use the data regularly collected by the client to progressively adapt the received model. But such naive approach exposes clients to the well-known problem of catastrophic forgetting. To address this problem, we have defined a Federated Continual Learning approach which is mainly based on distillation. Our approach allows a better use of resources, eliminating the need to retrain from scratch at the arrival of new data and reducing memory usage by limiting the amount of data to be stored. This proposal has been evaluated in the Human Activity Recognition (HAR) domain and has shown to effectively reduce the catastrophic forgetting effect.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity RecognitionContinual LearningFederated LearningHuman Activity RecognitionSimilar Papers 제목 키워드 기반
A distillation-based approach integrating continual learning and federated learning for pervasive services
Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach …
Activity RecognitionContinual LearningFederated LearningHuman Activity Recognition+1A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison
Pervasive computing promotes the installation of connected devices in our living spaces in order to provide services. Two major developments have gained significant momentum recently: an advanced use of edge resources an…
Activity RecognitionFederated LearningHuman Activity RecognitionSpecificityExplainability and Continual Learning meet Federated Learning at the Network Edge
As edge devices become more capable and pervasive in wireless networks, there is growing interest in leveraging their collective compute power for distributed learning. However, optimizing learning at the network edge en…
Continual LearningEdge-computingExplainable ModelsFederated Learning+2Opportunistic Federated Learning: An Exploration of Egocentric Collaboration for Pervasive Computing Applications
Pervasive computing applications commonly involve user's personal smartphones collecting data to influence application behavior. Applications are often backed by models that learn from the user's experiences to provide p…
Federated LearningFederated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domain
Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more gene…
Activity RecognitionFederated LearningHuman Activity Recognition