Federated Learning (FL) enables collaborative training while protecting the privacy of participant data. However, typical centralized FL structures are vulnerable to malicious client attacks. To mitigate such vulnerabilities, blockchain technology has been used to develop a decentralized FL framework. Yet, this approach leads to significant transmission and computation overhead. In order to improve robustness as well as efficiency, we propose Multi-Population Federated Learning (MPFL), which optimizes blockchain-based federated learning by incorporating operators of multi-population genetic algorithm (MPGA), such as selection, crossover, mutation and migration. Moreover, we introduce a committee consensus mechanism tailored to MPFL, where honest clients are elected to govern each population, thereby facilitating intraspecific and interspecific competition. Our experiments demonstrate that MPFL outperforms various aggregation algorithms in achieving superior robustness, and it reduces the costs of transmission and computation compared to the blockchain-based FL framework.

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for all the agents in a decentralized manner. Specifically, InforMARL aggregates information about the local neighborhood of agents for both the actor and the critic using a graph neural network and can be used in conjunction with any standard MARL algorithm. We show that (1) in training, InforMARL has better sample efficiency and performance than baseline approaches, despite using less information, and (2) in testing, it scales well to environments with arbitrary numbers of agents and obstacles. We illustrate these results using four task environments, including one with predetermined goals for each agent, and one in which the agents collectively try to cover all goals.

The fundamental intelligent reflecting surface (IRS) deployment problem is studied for IRS-aided downlink multi-user communication system, where IRSs are arranged to be deployed in a specific area for enhancing the desired signal and suppressing interference. Specifically, we aim to maximize the minimum achievable rate over all locations in a specific area by jointly optimizing the transmit beamforming at the access point (AP) as well as the placement and reflective beamforming at the IRS. The formulated problem is non-convex and thus difficult to be solved directly. To draw essential insights, we first consider the single-user case and the optimal solution is derived in closed-form. The result shows that the optimal locations are in the connecting line between the AP and user, and the IRSs can be optimally deployed along the connecting line. Besides, a hybrid offline and online design scheme is developed for the multi-user case, where an area discretization strategy and deep neural network (DNN)-based curve fitting technique are proposed for optimizing the IRS locations in the offline manner. Then, an online iterative algorithm is presented to solve the transmit and received beamformig vectors, respectively. Numerical results show that the performance gain is increased by optimizing the IRS locations.

The potential application of intelligent reflecting surfaces (IRSs) for future wireless cellular communication systems has motivated the study of metasurface for achieving additional space degree of freedom, where IRS is used to enhance the desired signal strength and suppress the interference. In this paper, by using the additional design degree of freedom provided by the IRS, we jointly optimize the transmit beamforming vector at the BS and the reflective beamforming vector at the IRS to maximize the minimum rate in the IRS-aided multi-user multiple-input-single-output broadcast channel (MISO-BC), subject to the unit modulus constraints of the reflective beamforming vector. In order to solve the non-convex optimization problem, we propose an efficient algorithm based on alternating optimization. In particular, we optimize the transmit beamforming vectors via the second-order cone problem (SOCP) and reflective beamforming vector by using the semi-definite relaxation (SDR). Numerical results show that the use of IRS leads to significant higher SINR values than benchmark schemes without IRS.