Abstract:In this paper, we investigate Bayesian model compression in federated learning (FL) to construct sparse models that can achieve both communication and computation efficiencies. We propose a decentralized Turbo variational Bayesian inference (D-Turbo-VBI) FL framework where we firstly propose a hierarchical sparse prior to promote a clustered sparse structure in the weight matrix. Then, by carefully integrating message passing and VBI with a decentralized turbo framework, we propose the D-Turbo-VBI algorithm which can (i) reduce both upstream and downstream communication overhead during federated training, and (ii) reduce the computational complexity during local inference. Additionally, we establish the convergence property for thr proposed D-Turbo-VBI algorithm. Simulation results show the significant gain of our proposed algorithm over the baselines in reducing communication overhead during federated training and computational complexity of final model.
Abstract:This paper investigates resource allocation to provide heterogeneous users with customized virtual reality (VR) services in a mobile edge computing (MEC) system. We first introduce a quality of experience (QoE) metric to measure user experience, which considers the MEC system's latency, user attention levels, and preferred resolutions. Then, a QoE maximization problem is formulated for resource allocation to ensure the highest possible user experience,which is cast as a reinforcement learning problem, aiming to learn a generalized policy applicable across diverse user environments for all MEC servers. To learn the generalized policy, we propose a framework that employs federated learning (FL) and prompt-based sequence modeling to pre-train a common decision model across MEC servers, which is named FedPromptDT. Using FL solves the problem of insufficient local MEC data while protecting user privacy during offline training. The design of prompts integrating user-environment cues and user-preferred allocation improves the model's adaptability to various user environments during online execution.
Abstract:Federated learning (FL) enables multiple clients to train a model while keeping their data private collaboratively. Previous studies have shown that data heterogeneity between clients leads to drifts across client updates. However, there are few studies on the relationship between client and global modes, making it unclear where these updates end up drifting. We perform empirical and theoretical studies on this relationship by utilizing mode connectivity, which measures performance change (i.e., connectivity) along parametric paths between different modes. Empirically, reducing data heterogeneity makes the connectivity on different paths more similar, forming more low-error overlaps between client and global modes. We also find that a barrier to connectivity occurs when linearly connecting two global modes, while it disappears with considering non-linear mode connectivity. Theoretically, we establish a quantitative bound on the global-mode connectivity using mean-field theory or dropout stability. The bound demonstrates that the connectivity improves when reducing data heterogeneity and widening trained models. Numerical results further corroborate our analytical findings.
Abstract:Model averaging, a widely adopted technique in federated learning (FL), aggregates multiple client models trained on heterogeneous data to obtain a well-performed global model. However, the rationale behind its success is not well understood. To shed light on this issue, we investigate the geometric properties of model averaging by visualizing the loss/error landscape. The geometrical visualization shows that the client models surround the global model within a common basin, and the global model may deviate from the bottom of the basin even though it performs better than the client models. To further understand this phenomenon, we decompose the expected prediction error of the global model into five factors related to client models. Specifically, we find that the global-model error after early training mainly comes from i) the client-model error on non-overlapping data between client datasets and the global dataset and ii) the maximal distance between the global and client models. Inspired by these findings, we propose adopting iterative moving averaging (IMA) on global models to reduce the prediction error and limiting client exploration to control the maximal distance at the late training. Our experiments demonstrate that IMA significantly improves the accuracy and training speed of existing FL methods on benchmark datasets with various data heterogeneity.
Abstract:With the growth of neural network size, model compression has attracted increasing interest in recent research. As one of the most common techniques, pruning has been studied for a long time. By exploiting the structured sparsity of the neural network, existing methods can prune neurons instead of individual weights. However, in most existing pruning methods, surviving neurons are randomly connected in the neural network without any structure, and the non-zero weights within each neuron are also randomly distributed. Such irregular sparse structure can cause very high control overhead and irregular memory access for the hardware and even increase the neural network computational complexity. In this paper, we propose a three-layer hierarchical prior to promote a more regular sparse structure during pruning. The proposed three-layer hierarchical prior can achieve per-neuron weight-level structured sparsity and neuron-level structured sparsity. We derive an efficient Turbo-variational Bayesian inferencing (Turbo-VBI) algorithm to solve the resulting model compression problem with the proposed prior. The proposed Turbo-VBI algorithm has low complexity and can support more general priors than existing model compression algorithms. Simulation results show that our proposed algorithm can promote a more regular structure in the pruned neural networks while achieving even better performance in terms of compression rate and inferencing accuracy compared with the baselines.
Abstract:The Metaverse has emerged to extend our lifestyle beyond physical limitations. As essential components in the Metaverse, digital twins (DTs) are the digital replicas of physical items. End users access the Metaverse using a variety of devices (e.g., head-mounted devices (HMDs)), mostly lightweight. Multi-access edge computing (MEC) and edge networks provide responsive services to the end users, leading to an immersive Metaverse experience. With the anticipation to represent physical objects, end users, and edge computing systems as DTs in the Metaverse, the construction of these DTs and the interplay between them have not been investigated. In this paper, we discuss the bidirectional reliance between the DT and the MEC system and investigate the creation of DTs of objects and users on the MEC servers and DT-assisted edge computing (DTEC). We also study the interplay between the DTs and DTECs to allocate the resources fairly and adequately and provide an immersive experience in the Metaverse. Owing to the dynamic network states (e.g., channel states) and mobility of the users, we discuss the interplay between local DTECs (on local MEC servers) and the global DTEC (on cloud server) to cope with the handover among MEC servers and avoid intermittent Metaverse services.
Abstract:Ambient backscatter communication (AmBC) leverages the existing ambient radio frequency (RF) environment to implement communication with battery-free devices. One critical challenge of AmBC systems is signal recovery because the transmitted information bits are embedded in the ambient RF signals and these are unknown and uncontrollable. To address this problem, most existing approaches use averaging-based energy detectors and consequently the data rate is low and there is an error floor. Here we propose a new detection strategy based on the ratio between signals received from a multiple-antenna Reader. The advantage of using the ratio is that ambient RF signals are removed directly from the embedded signals without averaging and hence it can increase data rates and avoid the error floor. Different from original ratio detectors that use the magnitude ratio of the signals between two Reader antennas, in our proposed approach, we utilize the complex ratio so that phase information is preserved and propose an accurate linear channel model approximation. This allows the application of existing linear detection techniques from which we can obtain a minimum distance detector and closed-form expressions for bit error rate (BER). In addition, averaging, coding and interleaving can also be included to further enhance the BER. The results are also general, allowing any number of Reader antennas to be utilized in the approach. Numerical results demonstrate that the proposed approach performs better than approaches based on energy detection and original ratio detectors.
Abstract:By employing powerful edge servers for data processing, mobile edge computing (MEC) has been recognized as a promising technology to support emerging computation-intensive applications. Besides, non-orthogonal multiple access (NOMA)-aided MEC system can further enhance the spectral-efficiency with massive tasks offloading. However, with more dynamic devices brought online and the uncontrollable stochastic channel environment, it is even desirable to deploy appealing technique, i.e., intelligent reflecting surfaces (IRS), in the MEC system to flexibly tune the communication environment and improve the system energy efficiency. In this paper, we investigate the joint offloading, communication and computation resource allocation for IRS-assisted NOMA MEC system. We firstly formulate a mixed integer energy efficiency maximization problem with system queue stability constraint. We then propose the Lyapunov-function-based Mixed Integer Deep Deterministic Policy Gradient (LMIDDPG) algorithm which is based on the centralized reinforcement learning (RL) framework. To be specific, we design the mixed integer action space mapping which contains both continuous mapping and integer mapping. Moreover, the award function is defined as the upper-bound of the Lyapunov drift-plus-penalty function. To enable end devices (EDs) to choose actions independently at the execution stage, we further propose the Heterogeneous Multi-agent LMIDDPG (HMA-LMIDDPG) algorithm based on distributed RL framework with homogeneous EDs and heterogeneous base station (BS) as heterogeneous multi-agent. Numerical results show that our proposed algorithms can achieve superior energy efficiency performance to the benchmark algorithms while maintaining the queue stability. Specially, the distributed structure HMA-LMIDDPG can acquire more energy efficiency gain than centralized structure LMIDDPG.
Abstract:The cloud-based solutions are becoming inefficient due to considerably large time delays, high power consumption, security and privacy concerns caused by billions of connected wireless devices and typically zillions bytes of data they produce at the network edge. A blend of edge computing and Artificial Intelligence (AI) techniques could optimally shift the resourceful computation servers closer to the network edge, which provides the support for advanced AI applications (e.g., video/audio surveillance and personal recommendation system) by enabling intelligent decision making on computing at the point of data generation as and when it is needed, and distributed Machine Learning (ML) with its potential to avoid the transmission of large dataset and possible compromise of privacy that may exist in cloud-based centralized learning. Therefore, AI is envisioned to become native and ubiquitous in future communication and networking systems. In this paper, we conduct a comprehensive overview of recent advances in distributed intelligence in wireless networks under the umbrella of native-AI wireless networks, with a focus on the basic concepts of native-AI wireless networks, on the AI-enabled edge computing, on the design of distributed learning architectures for heterogeneous networks, on the communication-efficient technologies to support distributed learning, and on the AI-empowered end-to-end communications. We highlight the advantages of hybrid distributed learning architectures compared to the state-of-art distributed learning techniques. We summarize the challenges of existing research contributions in distributed intelligence in wireless networks and identify the potential future opportunities.
Abstract:This paper leverages machine-learned predictions to design competitive algorithms for online conversion problems with the goal of improving the competitive ratio when predictions are accurate (i.e., consistency), while also guaranteeing a worst-case competitive ratio regardless of the prediction quality (i.e., robustness). We unify the algorithmic design of both integral and fractional conversion problems, which are also known as the 1-max-search and one-way trading problems, into a class of online threshold-based algorithms (OTA). By incorporating predictions into design of OTA, we achieve the Pareto-optimal trade-off of consistency and robustness, i.e., no online algorithm can achieve a better consistency guarantee given for a robustness guarantee. We demonstrate the performance of OTA using numerical experiments on Bitcoin conversion.