Federated learning collaboratively trains machine learning models among different clients while keeping data privacy and has become the mainstream for breaking data silos. However, the non-independently and identically distribution (i.e., Non-IID) characteristic of different image domains among different clients reduces the benefits of federated learning and has become a bottleneck problem restricting the accuracy and generalization of federated models. In this work, we propose a novel federated image segmentation method based on style transfer, FedST, by using a denoising diffusion probabilistic model to achieve feature disentanglement and image synthesis of cross-domain image data between multiple clients. Thus it can share style features among clients while protecting structure features of image data, which effectively alleviates the influence of the Non-IID phenomenon. Experiments prove that our method achieves superior segmentation performance compared to state-of-art methods among four different Non-IID datasets in objective and subjective assessment. The code is available at https://github.com/YoferChen/FedST.

Functional and inclusion dependency discovery is important to knowledge discovery, database semantics analysis, database design, and data quality assessment. Motivated by the importance of dependency discovery, this paper reviews the methods for functional dependency, conditional functional dependency, approximate functional dependency, and inclusion dependency discovery in relational databases and a method for discovering XML functional dependencies.

In the multicarrier direct-sequence code-division multiple access with repetition code system, decreasing the code rate can result in greater frequency diversity. However, to keep the same transmit bit rate, the spreading factor in each subcarrier needs to be reduced. In this paper, we use the outage probability as a criterion for these two system parameters' design. We first examine the condition on code rate for the uncorrelated fading channel assumption. The system performance is derived and the outage probability is obtained in closed forms for equal and unequal transmit bit energy scenarios. The relation between the spreading factor and the rate of the repetition code is investigated by observing the outage probability equation.