Vertical federated learning (VFL) enables a privacy-preserving collaboration among various parties to train a global model by melding their geo-distributed data features. Communication has been recognized as the primary bottleneck that impairs training efficiency due to frequent cross-party statistics exchange over wide area network. Existing synchronous VFL works often suffer from excessive communication overhead, while asynchronous schemes may introduce significant model staleness, potentially eroding the learning accuracy. In this paper, we propose BS-VFL, an asynchronous VFL with bounded staleness, to pipeline local computation and statistics transmission, substantially reducing the communication overhead while ensuring favorable model performance. Specifically, all data parties will give precedence to local model updates before generating embeddings to curtail model staleness. By analyzing convergence error, we show that BS-VFL can achieve a comparable result to synchronous VFL. Then, we develop a general framework to derive the closed-form wall-clock time of BS-VFL, offering a measure of its runtime efficiency and highlighting a marked communication reduction. Utilizing this convergence and time analysis, we refine learning parameters to minimize the convergence error for optimizing BS-VFL performance without compromising training efficiency. Extensive experiments on real-world datasets validate the superiority of BS-VFL over leading-edge methods, evidencing a reduction in training duration by 48%-90% while preserving model accuracy.

With the rapid growth of Low Earth Orbit (LEO) satellite networks, satellite-IoT systems using the LoRa technique have been increasingly deployed to provide widespread Internet services to low-power and low-cost ground devices. However, the long transmission distance and adverse environments from IoT satellites to ground devices pose a huge challenge to link reliability, as evidenced by the measurement results based on our real-world setup. In this paper, we propose a blind coherent combining design named B2LoRa to boost LoRa transmission performance. The intuition behind B2LoRa is to leverage the repeated broadcasting mechanism inherent in satellite-IoT systems to achieve coherent combining under the low-power and low-cost constraints, where each re-transmission at different times is regarded as the same packet transmitted from different antenna elements within an antenna array. Then, the problem is translated into aligning these packets at a fine granularity despite the time, frequency, and phase offsets between packets in the case of frequent packet loss. To overcome this challenge, we present three designs — joint packet sniffing, frequency shift alignment, and phase drift mitigation to deal with ultra-low SNRs and Doppler shifts featured in satellite-IoT systems, respectively. Finally, experiment results based on our real-world deployments demonstrate the high efficiency of B2LoRa.

Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads,packedHE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE assumes all clients share a single private key, making the system vulnerable to security threats of ciphertexts being intercepted and decrypted byhonest-but-curious clients. Also, it does not consider theheterogeneityamong different clients, resulting in undermined training efficiency with slow convergence and stragglers. To address these challenges, we propose FedPHE, a secure and efficient FL framework with PHE by jointly exploiting contribution-aware secure aggregation and straggler-resistant client selection. Using CKKS with sparsification and blinding, FedPHE achieves efficient secure aggregation that allows clients to only provideobscuredencrypted updates while the server can perform aggregation by accounting forcontributionsof local updates. To mitigate the straggler effect, we devise aperturbed sketch-based selection to cherry-pick representative clients withheterogeneous models and computing capabilitiesin a communication-efficient and privacy-preserving manner. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients' privacy, achieve$2.45-6.56\times$training speedup, cut the communication overhead by$1.32-24.85\times$, and reduce straggler effects by$1.89-2.78\times$.

Existing backdoor defense methods for federated learning (FL) usually try to distinguish between benign and malicious clients. The key insight is that benign clients are densely distributed, whereas malicious clients tend to be outliers outside this distribution. However, this only holds when data is independent and identically distributed (IID), and the effectiveness of these methods under non-IID data has not been systematically examined. In this paper, we present a comprehensive systematization of FL backdoor defense by breaking down its overall pipeline into three key components, i.e., metrics for evaluating clients, techniques for amplifying the difference between benign and malicious clients, and mechanisms for identifying malicious clients. We conduct an empirical study of FL backdoor defense methods under non-IID data settings to explore whether benign and malicious clients can be fully distinguished. Experimental results show that the defense performance degrades significantly when data is non-IID. Our results also reveal how evaluation metrics, amplification techniques and identification mechanisms perform under diverse settings. Contrary to the established belief, we further conclude that these defenses have inherent shortcomings, due to lack of stability and robustness in detecting malicious clients. We believe that our findings can better facilitate the development of FL backdoor defenses.

Pipeline parallelism has emerged as an indispensable technique for training large deep neural networks. While existing asynchronous pipeline systems address the time bubbles inherent in synchronous architectures, they continue to suffer frominefficiencyandsusceptibilitytovolatilehardware environment due to their suboptimal andstaticconfigurations. In this paper, we propose DynPipe, aninterference-awareasynchronous pipeline framework to optimize theend-to-endtraining performance in highlydynamiccomputing environments. By characterizing thenon-overlappedcommunication overheads andconvergencerate conditioned on stage-wise staleness, DynPipe carefully crafts an optimized pipeline partition that harmonizes the hardware speed with statistical convergence. Moreover, DynPipe deploys anon-intrusiverandom forest model that utilizes runtime stage statistics to evaluate the impact of environmental changes, such as task interference and network jitter, on the training efficiency. Following the evaluation guidance, DynPipe adaptivelyadjustspartition plan to restore both intra and inter-stage load balancing, thereby facilitating seamless pipeline reconfiguration in dynamic environments. Extensive experiments show that DynPipe outperforms state-of-the-art systems, accelerating the time-to-accuracy by1.5-3.4×.

Graph convolutional network (GCN) has achieved enormous success in learning structural information from unstructured data. As graphs become increasingly large, distributed training for GCNs is severely prolonged by frequent cross-worker communications. Existing efforts to improve the training efficiency often come at the expense of GCN performance, while the communication overhead persists. In this paper, we propose PSC-GCN, a holistic pipelined framework for distributed GCN training with communication-efficient sampling and inclusion-aware caching, to address the communication bottleneck while ensuring satisfactory model performance. Specifically, we devise an asynchronous pre-fetching scheme to retrieve stale statistics (features, embedding, gradient) of boundary nodes in advance, such that the embedding aggregation and model update are pipelined with statistics transmission. To alleviate communication volume and staleness effect, we introduce a variance-reduction based sampling policy, which prioritizes inner nodes over boundary ones for reducing the access frequency to remote neighbors, thus mitigating cross-worker statistics exchange. Complementing graph sampling, a feature caching module is co-designed to buffer hot nodes with high inclusion probability, ensuring that frequently sampled nodes will be available in local memory. Extensive evaluations on real-world datasets show the superiority of PSC-GCN over state-of-the-art methods, where we can reduce training time by 72%-80% without sacrificing model accuracy.

Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing their private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE does not consider the heterogeneity among different clients, an intrinsic problem in cross-silo FL, often resulting in undermined training efficiency with slow convergence and stragglers. In this work, we propose FedPHE, an efficiently packed homomorphically encrypted FL framework with secure weighted aggregation and client selection to tackle the heterogeneity problem. Specifically, using CKKS with sparsification, FedPHE can achieve efficient encrypted weighted aggregation by accounting for contributions of local updates to the global model. To mitigate the straggler effect, we devise a sketching-based client selection scheme to cherry-pick representative clients with heterogeneous models and computing capabilities. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients’ privacy, achieve a training speedup of 1.85 − 4.44×, cut the communication overhead by 1.24 − 22.62× , and reduce the straggler effect by up to 1.71 − 2.39×.

Mobile edge computing facilitates users to offload computation tasks to edge servers for meeting their stringent delay requirements. Previous works mainly explore task offloading when system-side information is given (e.g., server processing speed, cellular data rate), or centralized offloading under system uncertainty. But both generally fall short of handling task placement involving many coexisting users in an uncertain environment. In this paper, we develop amulti-useroffloading framework consideringunknown yet stochasticsystem-side information to enable adecentralized user-initiatedservice placement under overlapping server coverage. Specifically, we formulate the dynamic task placement as an online multi-user multi-armed bandit process, and propose a decentralized epoch based offloading (DEBO) to optimize user rewards which are subjected under network delay. We consider both cases without and with neighboring edge feedback once users’ tasks are processed, where the latter incorporates system-side information sharing among edge servers for an enhanced task placement. For both cases, we show that DEBO can gradually deduce the optimal user-server assignment during dynamic offloading, thereby achieving aclose-to-optimalservice performance andtight$O(\log _{2}\!\!T)$regret. Moreover, we generalize DEBO to various common scenarios such as unknown reward gap, dynamic entering or leaving of clients, and fair reward distribution, while further exploring when users’ offloaded tasks requireheterogeneouscomputing resources. Particularly, we accomplish a sub-linear regret for each of these instances. Real measurements based evaluations corroborate the superiority of our offloading schemes over state-of-the-art approaches in optimizing delay-sensitive rewards.

Mobile edge computing (MEC) facilitates computation offloading to edge server and task processing via device-to-device (D2D) collaboration. Existing works mainly focus on centralized network-assisted offloading solutions, which are unscalable to collaborations among massive users. In this paper, we propose a joint framework of decentralized D2D collaboration and task offloading for MEC systems with large populations. Specifically, we utilize the power of two choices for D2D collaboration, which enables users to assist each other in a decentralized manner. Due to short-range D2D communication and user movements, we formulate a mean field model on a finite-degree and dynamic graph to analyze the collaboration state evolution. We derive the existence, uniqueness and convergence of the state stationary point to provide a tractable collaboration performance. Complementing this D2D collaboration, we further build a Stackelberg game to model users’ task offloading, where the provider, managing many servers, is the leader to determine service prices, while users are followers to make offloading decisions. By embedding Stackelberg game into Lyapunov optimization, we develop an online offloading and pricing scheme, which can optimize servers’ service utility or fairness, and users’ system cost simultaneously. Extensive evaluations show that D2D collaboration can mitigate users’ workloads by 73.8% and fair pricing can promote servers’ utility fairness by 15.87%.

Although federated learning (FL) enables collaborative training across multiple data silos in a privacy-protected manner, naively minimizing the aggregated loss to facilitate an efficient federation may compromise its fairness. Many efforts have been devoted to maintaining similar average accuracy across clients by reweighing the loss function while clients’ potential contributions are largely ignored. This, however, is often detrimental since treating all clients equally will harm the interests of those clients with more contribution. To tackle this issue, we introduce utopian fairness to expound the relationship between individual earning and collaborative productivity, and proposeFederated-UtoPia (FedUP), a novel FL framework that balances both efficient collaboration and fair aggregation. For the distributed collaboration, we model the training process among strategic clients as a supermodular game, which facilitates a rational incentive design through the optimal reward. As for the model aggregation, we design a weight attention mechanism to compute the fair aggregation weights by minimizing the performance bias among heterogeneous clients. Particularly, we utilize the alternating optimization theory to bridge the gap between collaboration efficiency and utopian fairness, and theoretically prove that FedUP has fair model performance with fast-rate training convergence. Extensive experiments using both synthetic and real datasets demonstrate the superiority of FedUP.

Effective incentive mechanisms are invaluable in crowdsensing to stimulate the enthusiasm of strategic users. However, existing work focusing on multi-task allocation with the objective of purely maximizing the social utility may result in the problem of unbalanced allocation, which may damage the social fairness. This motivates us to introduce proportional fairness into the design of a novel fairness-aware incentive mechanism for the first time. Specifically, we first model the interaction of multi-task allocation in crowdsensing as a multi-requester multi-worker Stackelberg game, and then transform the fairness-aware multi-task allocation problem into a fairness-aware incentive mechanism design problem. Next, we prove that there is a unique Stackelberg equilibrium, and also show that it can be efficiently derived through cautiously proposed algorithms. Since the existing equilibrium may not be optimal, we further design a secondary allocation rule to maximize both social utility and system performance, while achieving proportional fairness at a minimum cost. Finally, extensive experiments using both synthetic and real-world datasets demonstrate the superiority of our proposed mechanism compared to the state of the arts.

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients' selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal O(T - 2/3) convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques. © 2023 IEEE.

IoT uplink performance is crucial for a wide variety of IoT applications such as health sensing and industrial control, which demand reliable delivery of sensor data to the cloud. However, due to the limited transmission power budget imposed on many power-constrained IoT devices, IoT uplinks are highly susceptible to cross-technology interference (CTI) caused by coexisting networks. Previous approaches to mitigating CTI have relied on MAC/PHY designs. They suffer from poor performance and limited generality in the presence of wideband CTI sources such as Wi-Fi and RF jammer, which transmit aggressively on large spectrum chunks using diverse radio technologies.

Mobile chargers (MCs) are usually dispatched to deliver energy to sensors in wireless rechargeable sensor networks (WRSNs) due to its flexibility and easy maintenance. This paper concerns the fundamental issue of charging path DEsign with the Minimized energy cOst (DEMO), i.e., given a set of rechargeable sensors, we appropriately design the MC’s charging path to minimize the energy cost which is due to the wireless charging and the MC’s movement, such that the different charging demand of each sensor is satisfied. Solving DEMO is NP-hard and involves handling the tradeoff between the charging efficiency and the moving cost. To address DEMO, we first investigate how to identify a single charging position where the MC could stay to charge a set of sensors distributed within a small area with the maximized charging efficiency. Then, based on the result obtained in the case of optimizing a single charging position, we develop a computational geometry-based algorithm to deploy multiple charging positions within the whole network, by considering the fixed and finite charging range of the MC. We prove that the designed algorithm has the approximation ratio of$O\!\left ({\ln \!N}\right)$, where$N$is the number of sensors. Then we construct the charging path by calculating the shortest Hamiltonian cycle passing through all the deployed charging positions within the network. In addition, we investigate the impact of the network topology as well as the distribution of charging demands among sensors on the MC’s energy cost during a charging tour. Extensive evaluations validate the superiority of our path design in terms of the MC’s energy cost minimization, compared with existing main algorithms.

As the most widely used outdoor navigation system, GPS can provide accurate localization on the horizontal plane. However, the vertical localization accuracy exhibits a poor performance. Vehicles on the elevated road usually receive wrong navigation instructions since GPS fails to detect vehicles' vertical location. In this paper, we present a vertical location system named VLD for vehicles in metropolises mainly leveraging smartphones' barometers, a low-power sensor found in an increasing number of smart devices. When initially on the ground, VLD combines the height and angle detection algorithms to confirm the vertical location with low complexity. Once vehicles have exited the ground and start to travel on the elevated road, a pressure-height model trained by a novel proposed sensor fusion algorithm is activated to measure vehicles' relative height. Then, it tracks the relative height in real time according to a pressure-temperature model which is calibrated by current weather. Comparing the relative height with the single-level elevated road's height, VLD can determine which level vehicles travel on in many highway interchanges and when they exit the elevated road. Experiments covering one month demonstrate that the detection accuracy of VLD exceeds 99% under different weather conditions, and it shows a more accurate relative height measurement compared to available literature, including Baidu Maps and one barometer based application-Altitude. Finally, VLD demonstrates a high efficiency with respect to both the detection delay and power consumption.

LoRa, which is considered as an appealing wireless technique for Low-Power Wide-Area Networks (LPWANs), has found wide applications in fields such as smart cities, intelligent agriculture. Despite its popularity, there exists a growing concern about secure communications mainly due to the free frequency band and minimalist design specified in LoRa communications. For example, an attacker can forge messages to launch spoofing attack. To mitigate the threat, an authentication mechanism is needed. In this paper, we propose a lightweight node authentication scheme named SLoRa for LoRa networks by leveraging two physical layer features-Carrier Frequency Offset (CFO) and spatial-temporal link signature. In particular, we propose a novel CFO compensation algorithm, and identify slight CFO variations by adopting linear fitting for received upchirps to mitigate the noise's randomness on fine-grained CFO estimation. Besides, we can obtain fine-grained link signatures without the conventional de-convolution operation based on the theoretical analysis. Then, we show how these two physical-layer features complement each other to conquer the drift challenge brought by weather and environment variations. Combining these two features, SLoRa can distinguish whether the received signal is conveyed from a legitimate LoRa node or not. Experiments covering indoor and outdoor scenarios are conducted to demonstrate a high accuracy for node authentication in SLoRa, which is around 97% indoors and 90% outdoors.

We present mLoRa in this paper, a novel protocol that can decode multiple collided packets simultaneously from different transmitters in LoRa networks. As a recently proposed wireless technology designed for low-power wide-area networks, LoRa has been proverbially employed in many fields, such as smart cities, intelligent agriculture, and environmental monitoring. In LoRa networks, a star-of-stars topology is conventionally implemented, in which thousands of nodes connect to a single gateway. Accordingly, the convergecast scenario becomes common. For example, in intelligent agriculture, multiple sensor nodes send information with respect to the soil temperature and humidity to a LoRa gateway. Regularly, simultaneous transmissions result in the severe collision problem. Meanwhile, the ALOHA protocol is widely applied in LoRa networks, which further aggravates the collision problem. To conquer this challenge, we propose a protocol named mLoRa for multi-packet reception in LoRa networks, leveraging unique features inherent in LoRa’s physical layer including chirp spread spectrum (CSS), M-FSK modulation, and demodulation. In addition, design enhancements are developed to mitigate the noise and frequency offset influence. We implement mLoRa on a six-node testbed with USRPs. Experiment results demonstrate that mLoRa enables up to three concurrent transmissions. Correspondingly, mLoRa based throughput is around 3 times more than the conventional LoRa.

With the increase of data driven vehicular applications, existing networks cannot satisfy the communication requirements. Therefore, 5G millimeter wave (mmWave) communications, which can offer multi-gigabit data rate, hold potential to be utilized in vehicular networks. On one hand, due to the densely deployed 5G base stations, frequent handover will largely decrease the quality of service, where recent handover is at hundred-millisecond level. On the other hand, mmWave links are easily broken by obstacles because of short wavelength. Yet existing handover protocols do not consider the blockage problem, which frequently occurs in mmWave based networks. To address these problems, we propose a real-time handover protocol called mmHandover for 5G mmWave vehicular networks leveraging mmWave antennae. In mmHandover, multiple antennae in one array are divided into two parts: pre-connected antennae and data transmission antennae. In parallel, pre-connected antennae build the connection with multiple candidate base stations before activation based on a designed pre-connection strategy, while data transmission antennae are responsible for data delivery with the currently connected base station. When handover is triggered or blockage happens, one of the pre-connected links will convert into data transmission link, thus realizing almost seamless handover. Finally, real data-driven simulations demonstrate the efficiency and effectiveness of mmHandover. Compared with standard 4G/WiFi handover protocols, mmHandover greatly reduces the delay from more than 500μs to about 1000μs. Besides, the delay gap will get widened coupled with increase in the number of vehicles.

Modern high-end scientific and technological robots have been utilized in various fields. With regard to distribution, reliability, flexibility, and economy, swarm robots can accomplish more arduous tasks in parallel and demonstrate a superior performance compared to single robot. However, information interaction, which causes extra time overhead, is essential to realize synchronization or coordination in multi robot system. This paper focuses on improving the edge coverage ability of base stations especially when swarm robots cover a wide range. It proposes a novel collaborative communication protocol named Co2-Robot for these robots in order to carry out distributed beamforming, thus enhancing the coverage range. In particular, efficient strategies are designed to cut down the time overhead among swarm robots. Subsequently, we develop a novel cluster head selection scheme to be responsible for the parallel operations. Then, distributed beamforming is performed to improve the uplink coverage when no signal from anyone of swarm robots can reach the base station. In addition, several practical user-cases are considered and analyzed in distributed beamforming, in order to enhance the robustness of this parallel system. Finally, extensive simulations show that Co2-Robot will just result in a small amount of time overhead, which is acceptable in most scenarios. Furthermore, it can substantially extend the coverage range up to nearly 1000m while single robot can just cover a coverage range of more than 100m.