FedTKD: A Trustworthy Heterogeneous Federated Learning Based on Adaptive Knowledge Distillation.

Federated learning allows multiple parties to train models while jointly protecting user privacy. However, traditional federated learning requires each client to have the same model structure to fuse the global model. In real-world scenarios, each client may need to develop personalized models based on its environment, making it difficult to perform federated learning in a heterogeneous model environment. Some knowledge distillation methods address the problem of heterogeneous model fusion to some extent. However, these methods assume that each client is trustworthy. Some clients may produce malicious or low-quality knowledge, making it difficult to aggregate trustworthy knowledge in a heterogeneous environment. To address these challenges, we propose a trustworthy heterogeneous federated learning framework (FedTKD) to achieve client identification and trustworthy knowledge fusion. Firstly, we propose a malicious client identification method based on client logit features, which can exclude malicious information in fusing global logit. Then, we propose a selectivity knowledge fusion method to achieve high-quality global logit computation. Additionally, we propose an adaptive knowledge distillation method to improve the accuracy of knowledge transfer from the server side to the client side. Finally, we design different attack and data distribution scenarios to validate our method. The experiment shows that our method outperforms the baseline methods, showing stable performance in all attack scenarios and achieving an accuracy improvement of 2% to 3% in different data distributions.

Development of the Nurses' Willingness to Engage in Palliative Care Scale.

Nurses play an important role in palliative care, and their willingness to engage in such work is thus crucial. The purpose of this study was to develop, and test the reliability and validity of, the Nurses' Willingness to Engage in Palliative Care Scale. The sample consisted of 224 Chinese nurses with a mean age of 32.36 (SD, 5.986) years. The critical ratio method was used for item analysis. Reliability was assessed by calculating Cronbach α. Content validity was assessed by calculating a content validity index based on ratings from 5 nursing experts. Structural validity was calculated by exploratory factor analysis. The developed scale consists of 20 items over 4 dimensions (attitude toward the behavior, subjective norms, perceived behavioral control, and behavioral intention) and has high content validity (0.97). The reliability of the scale was found to be sufficient (Cronbach α = .896). Four common factors were extracted from exploratory factor analysis, and the cumulative variance explained was 68.938%. The Nurses' Willingness to Engage in Palliative Care Scale has good reliability and validity and can be used to assess nurses' willingness to work in palliative care units.