Search

In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained large language model (LLM) using human language. In a multi-agent remote navigation task, with multimodal input data comprising location and channel maps, it is shown that EC incurs high training cost and struggles when using multimodal data, whereas LSC yields high inference computing cost due to the LLM's large size. To address their respective bottlenecks, we propose a novel framework of language-guided EC (LEC) by guiding the EC training using LSC via knowledge distillation (KD). Simulations corroborate that LEC achieves faster travel time while avoiding areas with poor channel conditions, as well as speeding up the MADRL training convergence by up to 61.8% compared to EC.

Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this void, in this article we propose, for the first time, a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog). This transformation is viable by extracting and merging common CMs and their connections while treating the NPM as a CM generator. By extensive simulations, we corroborate that the SPM tightly approximates its original NPM while occupying only 0.02% memory. By leveraging its interpretability and memory-efficiency, we demonstrate several SPM-enabled applications such as SPM reconfiguration for collision-avoidance, as well as comparing different SPMs via semantic entropy calculation and storing multiple SPMs to cope with non-stationary environments.

The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network. Federated learning (FL) has recently been applied in LotteryFL to discover such winning tickets in a distributed way, showing higher accuracy multi-task learning than Vanilla FL. Nonetheless, LotteryFL relies on unicast transmission on the downlink, and ignores mitigating stragglers, questioning scalability. Motivated by this, in this article we propose a personalized and communication-efficient federated lottery ticket learning algorithm, coined CELL, which exploits downlink broadcast for communication efficiency. Furthermore, it utilizes a novel user grouping method, thereby alternating between FL and lottery learning to mitigate stragglers. Numerical simulations validate that CELL achieves up to 3.6% higher personalized task classification accuracy with 4.3x smaller total communication cost until convergence under the CIFAR-10 dataset., Comment: 5 pages, 2 figures, 2 tables

Due to the edge's position between the cloud and the users, and the recent surge of deep neural network (DNN) applications, edge computing brings about uncertainties that must be understood separately. Particularly, the edge users' locally specific requirements that change depending on time and location cause a phenomenon called dataset shift, defined as the difference between the training and test datasets' representations. It renders many of the state-of-the-art approaches for resolving uncertainty insufficient. Instead of finding ways around it, we exploit such phenomenon by utilizing a new principle: AI model diversity, which is achieved when the user is allowed to opportunistically choose from multiple AI models. To utilize AI model diversity, we propose Model Diversity Network (MoDNet), and provide design guidelines and future directions for efficient learning driven communication schemes., Comment: 7 pages, 5 figures, 1 table

Are 5G connection and UAVs merely parts of an extravagant and luxurious world, or are they essential parts of a practical world in a way we have yet to see? To aid in a direction to address the issue, we provide a practical framework for immersive aerial monitoring for public safety. Because the framework is built on top of actual realizations and implementations designed to fulfill specific use cases, high level of practicality is ensured by nature. We first investigate 5G network performance on UAVs by isolating performance for different aspects of expected flight missions. Finally, the novel aerial monitoring scheme that we introduce relies on the recent advances brought by 5G networks and mitigates the inherent limitations of 5G network that we investigate in this paper., Comment: 6 pages, 6 figures, submitted to IEEE WCNCW 2020