5 papers
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
Thinh T. H. Nguyen, Le-Tuan Nguyen, Minh-Duong Nguyen +4
Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are difficu…
Memory-efficient Continual Learning with Prototypical Exemplar Condensation
Minh-Duong Nguyen, Thien-Thanh Dao, Le-Tuan Nguyen +2
Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on opt…
Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression
Minh-Duong Nguyen, Senura Hansaja, Le-Tuan Nguyen +4
Federated Unlearning (FUL) aims to remove specific participants' data contributions from a trained Federated Learning model, thereby ensuring data privacy and compliance with regul…
Communication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptation
Le-Tuan Nguyen, Minh-Duong Nguyen, Seon-Geun Jeong +2
With the rapid emergence of foundation models and the increasing need for fine-tuning across distributed environments, Federated Low-Rank Adaptation (FedLoRA) has recently gained s…
Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coreset
Minh-Duong Nguyen, Le-Tuan Nguyen, Quoc-Viet Pham
Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. T…