Recently, with the maturity of edge-cloud computing and the large amount of data generated in the edge, we have witnessed an increasing number of applications conducting collaborative learning and data analytics in networked edge systems. On the other end of the spectrum, there are also fast-growing concerns on privacy on using the data in the edge, which belong to diverse owners. Federated learning (FL) and federated analytics (FA), coined together as federated optimizations by Google, are new distributed computing techniques to address such a mismatch. In federated optimization, raw data are kept local and only the focused updates (weights or data insights) generated from local analytics are sent to a cloud server for result aggregation.