[HTML][HTML] Centralised vs. decentralised federated load forecasting in smart buildings: Who holds the key to adversarial attack robustness?

HU Manzoor, S Hussain, D Flynn, A Zoha - Energy and Buildings, 2024 - Elsevier
The integration of AI and ML into energy forecasting is crucial for modern energy
management. Federated Learning (FL) is particularly noteworthy because it enhances data …

Diffusion-driven data replay: A novel approach to combat forgetting in federated class continual learning

J Liang, J Zhong, H Gu, Z Lu, X Tang, G Dai… - … on Computer Vision, 2024 - Springer
Abstract Federated Class Continual Learning (FCCL) merges the challenges of distributed
client learning with the need for seamless adaptation to new classes without forgetting old …

Unleashing the power of continual learning on non-centralized devices: A survey

Y Li, H Wang, W Xu, T **ao, H Liu, M Tu… - arxiv preprint arxiv …, 2024 - arxiv.org
Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for
enabling distributed devices such as vehicles and servers to handle streaming data from a …

Overcoming Spatial-Temporal Catastrophic Forgetting for Federated Class-Incremental Learning

H Yu, X Yang, X Gao, Y Feng, H Wang… - Proceedings of the 32nd …, 2024 - dl.acm.org
This paper delves into federated class-incremental learning (FCiL), where new classes
appear continually or even privately to local clients. However, existing FCiL methods suffer …

Rehearsal-free continual federated learning with synergistic regularization

Y Li, Y Wang, T **ao, H Wang, Y Qi, R Li - arxiv preprint arxiv:2412.13779, 2024 - arxiv.org
Continual Federated Learning (CFL) allows distributed devices to collaboratively learn novel
concepts from continuously shifting training data while avoiding knowledge forgetting of …

A multifaceted survey on federated learning: Fundamentals, paradigm shifts, practical issues, recent developments, partnerships, trade-offs, trustworthiness, and ways …

A Majeed, SO Hwang - IEEE Access, 2024 - ieeexplore.ieee.org
Federated learning (FL) is considered a de facto standard for privacy preservation in AI
environments because it does not require data to be aggregated in some central place to …