Federated learning (FL) enables collaborative learning between parties, called clients, without sharing the original and potentially sensitive data. To ensure fast convergence in the presence of such heterogeneous clients, it is imperative to timely select clients who can effectively contribute to learning. A realistic but overlooked case of heterogeneous clients are Mavericks, who monopolize the possession of certain data types, e.g., children hospitals possess most of the data on pediatric cardiology. In this paper, we address the importance and tackle the challenges of Mavericks by exploring two types of client selection strategies. First, we show theoretically and through simulations that the common contribution-based approach, Shapley Value, underestimates the contribution of Mavericks and is hence not effective as a measure to select clients. Then, we propose FedEMD, an adaptive strategy with competitive overhead based on the Wasserstein distance, supported by a proven convergence bound. As FedEMD adapts the selection probability such that Mavericks are preferably selected when the model benefits from improvement on rare classes, it consistently ensures the fast convergence in the presence of different types of Mavericks. Compared to existing strategies, including Shapley Value-based ones, FedEMD improves the convergence speed of neural network classifiers with FedAvg aggregation by 26.9% and its performance is consistent across various levels of heterogeneity.

@en

Passive multifrequency microwave sensors frequently struggle with difficulties of nonuniform spatial resolution among multiple channels. The raw measurements in the land-sea transition zone are seriously contaminated. Conventional analytical deconvolution techniques suffer from the tradeoff between spatial resolution enhancement and noise amplification, leading to low data integrity in the practical spatial resolution matching application. To provide multichannel microwave radiometer (MWR) data with matching levels of spatial resolution, a method based on iterative deconvolution with close loop priors (ICLP) is proposed. Specifically, a destriping module is first utilized as a preprocessing step to maintain high data integrity. Then, the close loop mechanism using sparse adaptive priors is proposed to balance the spatial resolution and data integrity enhancement. Also, progressively iterative deconvolution is introduced to realize controllable levels of spatial resolution enhancement (spatial resolution matching) for multichannel data to reach a consistent level. Experiments performed using both simulated and actual microwave radiation imager (MWRI) data demonstrate the validity and effectiveness of the method.

@en

Energy demand growth in Asian countries is predicted to be the highest in the world. One of the drivers of energy demand growth is urbanization. Along with growing urban areas, public infrastructure, such as streetlights, is also expanding. Unfortunately, energy conservation measures in public facilities are commonly constrained by the budget limitations of local governments, while the potential participation of energy service companies (ESCO) requires regulation reformation settling the contradicting regulations. This study proposes several policy recommendations to modify existing guidelines for selecting ESCOs for the energy efficiency of streetlights in Indonesia that has the highest urbanization rate. Regulation review and several potential improvements for selecting ESCOs are provided. In 2017, the Ministry of Domestic Affairs released a Circular Letter to solve barriers to ESCO businesses in public sectors; however, the Circular Letter could be improved in several ways by eliminating the clauses on the holder of intellectual property rights, revising the valuation of economic benefit bidding, and increasing the maximum contract period. Moreover, we propose the use of smart street lighting technologies to improve the value-added services of streetlights and the establishment of a super ESCO to accelerate ESCO business activity in all economic sectors.@en