DA-PFL: Dynamic Affinity Aggregation in Personalized Federated Learning Under Class Imbalance.

Personalized federated learning (PFL) has become a hot research topic that can learn a personalized learning model for each client. Existing PFL models prefer to aggregate similar clients with similar data distribution to improve the performance of learning models. However, similarity-based PFL methods may exacerbate the class imbalance problem.

Knowledge, attitudes and practice regarding environmental friendly disinfectants for household use among residents of China in the post-pandemic period.

Background: A sharp rise in household consumption of disinfectants triggered by COVID-19 pandemic has generated tremendous environmental burden and risks of disinfectant emissions in the post-pandemic period. To address this emerging challenge, replacing highly hazardous disinfectants with more environmental friendly alternatives has been accepted as an inherently effective solution to environment issues posed by disinfectant emerging contaminants. However, no study has yet been done to explore the potential customers' attitudes and the market prospect of environmental friendly disinfectants until now.