2 papers
cs.LG2024
Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server
Fei Li, Chu Kiong Loo, Wei Shiung Liew +1
In federated learning, data heterogeneity significantly impacts performance. A typical solution involves segregating these parameters into shared and personalized components, a con…
cs.LG2023
Explainable Lifelong Stream Learning Based on "Glocal" Pairwise Fusion
Chu Kiong Loo, Wei Shiung Liew, Stefan Wermter
Real-time on-device continual learning applications are used on mobile phones, consumer robots, and smart appliances. Such devices have limited processing and memory storage capabi…