Considering the hardware-friendly characteristics, structured pruning has emerged as an effective solution to reduce the resource requirements of large language models (LLMs) on resource-constrained devices. Since pruning a certain number of parameters will often reduce the model accuracy, fine-tuning is usually required to recover performance loss. However, fine-tuning relies on high device power and substantial data, making it unsuitable for on-device applications. Recent approaches propose post-training structured pruning techniques that do not require fine-tuning, following three granularities,i.e., neurons, attention heads, and layers. Unfortunately, the previous solutions still suffer from the high memory overhead of substructures' importance evaluation at different granularities and the problem of only applying to models with specific structures, which limit their scope of applications. This paper proposes COMP, a lightweight and general post-training structured hybrid-granularity pruning method designed for on-device applications. COMP begins by assessing the importance of model layers and neurons individually using distributional distance and the matrix condition number. Subsequently, COMP performs fine-grained neuron pruning and simultaneously determines whether to apply coarse-grained layer pruning or not by comparing the outcomes of the two granularity strategies. Furthermore, COMP implements mask tuning to restore model accuracy without additional fine-tuning, minimizing dependency on external data resources and device power. Experimental results demonstrate that COMP performs well across models with various architectures. When pruning 20% of LLaMA-2-13B parameters, COMP requires less than 8 GB of memory, maintaining more than 90% model accuracy. Meanwhile, COMP improves performance by 3.54% compared to LLM-Pruner, while reducing memory overhead by 90%.

Federated learning (FL) enables multiple clients to collaboratively train models without exposing raw data. However, most FL research assumes that all clients have fully labeled data, which is impractical for many real-world applications. To this end, we focus on semi-supervised FL (SSFL), where data samples of each client are partially labeled. Existing SSFL methods often ignore three inherent characteristics of FL: limited communication resources, data heterogeneity and system heterogeneity, which severely hinder convergence stability and efficiency. This paper proposes E-FedAC, a novel SSFL framework that tackles these challenges through alternating client-to-client (C2C) collaboration. Specifically, E-FedAC employs a two-stage clustering strategy in each training round while concurrently considering differences in client computing/communication capabilities to mitigate the impact of intra-cluster stragglers. The first stage employs similarity clustering to group clients based on local data distribution, which allows similar clients to share knowledge and generate high-quality pseudo-labels for unlabeled data. In the second stage, clients are re-grouped using a dissimilarity clustering strategy to approximate the IID setting at the cluster level, thereby alleviating the bias induced by Non-IID data. E-FedAC utilizes a reinforcement learning algorithm to adaptively determine the average number of intra-cluster iterations across all clusters for both clustering stages, balancing between labeling assistance from similar clients and unbiased optimization from dissimilar clients. Additionally, E-FedAC dynamically optimizes local updating frequencies for each generated cluster based on this average and individual cluster capabilities, further reducing the waiting time across clusters. Extensive evaluations demonstrate that E-FedAC can provide up to 4.02× speedup and 61.74% savings in communication costs compared with existing benchmarks.

Recently, aided by edge computing (EC), federated meta-learning (FML) has been proposed to adequately utilize personalized data on different edge devices by incorporating meta-learning with federated learning (FL). Unlike conventional FL which conducts several stochastic gradient descent (SGD) steps to directly update the local model in each training round, FML first performs some SGDsteps to obtain a reference model and then performs a meta-step to update the local model along the direction towards the reference model. In this way, FML can identify common patterns and structures across different clients (i.e., edge devices) and quickly adapt to new data distributions, which exhibits its advantage in dealing with statistical heterogeneity inherent in FL. However, existing FML approaches struggle to effectively cope with two key challenges: i) the disparity in dataset informativeness among clients with statistically heterogeneous local data; and ii) the disparity in computing capacities among clients with heterogeneous hardware configurations. Herein, we propose a heterogeneity-aware FML framework, termed HFML, which explores adjusting the execution frequencies of SGD step and meta-step in each training round to address the above statistical and system heterogeneity challenges simultaneously. We introduce usable information (UI) as a new metric in HFML to quantify dataset informativeness, and theoretically analyze the influence of the execution frequencies of SGD steps and meta-steps on model performance and convergence speed. Based on the theoretical analysis, we develop an efficient optimization algorithm to jointly adjust the execution frequencies for different clients to handle the heterogeneity issues, which contributes to accelerating model training and enhancing personalization performance. Experimental results demonstrate that HFML can speed up training by up to 4.02× and improve model accuracy by an average of 11.5% compared to the baselines under heterogeneous settings.

Recently, Split Federated Learning (SFL) advances typical Federated Learning (FL) and offers a feasible solution by splitting a full model into a bottom model (for clients) and a top model (for the server), which alleviates the computation and/or communication burden on clients. However, existing SFL works often assume sufficient labeled data on clients, which is usually impractical. Besides, non-IID data poses another challenge to ensure efficient model training. To our best knowledge, the above two data-related issues have not been simultaneously addressed in SFL. Herein, we review the distinct properties of SFL and develop a novel Semi-supervised SFL system, called SemiSFL. In SemiSFL, a student bottom model and a teacher bottom model are assigned to each client, while the server maintains the top parts and full versions of both the global and teacher models. Cross-entity (i.e., clients and the server) semi-supervised training and server-side supervised training are alternately conducted. During semi-supervised training, we explore regularizing the student features (produced by student bottom models) from different clients with the teacher features (produced by teacher bottom models) before conducting semi-supervised training, so as to improve the generalization ability of student bottom models. Moreover, our theoretical and experimental investigations reveal that the inconsistent training processes on labeled and unlabeled data have an influence on the effectiveness of SemiSFL. To mitigate training inconsistency, we develop an algorithm for dynamically regulating the frequency of performing server-side supervised training. Extensive experiments on benchmark models and datasets show that SemiSFL provides a 3.8× speed-up in training time, reduces the communication cost by about 70.3% while reaching the target accuracy, and achieves up to 5.8% improvement in accuracy under different non-IID settings compared to the state-of-the-art baselines.

Federated fine-tuning (FedFT) has become a decentralized approach for fine-tuning pre-trained large language models(LLMs). However, due to the immense size of LLMs, there are two critical challenges for efficient FedFT in practice, i.e., resource constraints and system heterogeneity. Though existing approaches employ low-rank adaptation (LoRA) method, to mitigate fine-tuning overhead, they still suffer from high memory consumption and large training latency. According to the characteristics of FedFT, we observe that appropriate quantization and LoRA configurations can reduce resource consumption while maintaining comparable model performance. Consequently, we propose an efficient FedFT framework, termed FedQLoRA, which dynamically adjusts the quantization level and LoRA depth during training. This design enables large models to be fine-tuned on resource-limited devices while reducing training latency and preserving model performance. Extensive experimental results demonstrate that FedQLoRA achieves up to 70.34% reduction in training time and$62.71 \%-77.50 \%$savings in memory consumption compared to baseline methods.

Federated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications,i.e., resource constraints and system heterogeneity. Existing works rely on parameter-efficient fine-tuning methods,e.g., low-rank adaptation (LoRA), but with major limitations. Herein, based on the inherent characteristics of FedFT, we observe that LoRA layers with higher ranks added close to the output help to save resource consumption while achieving comparable fine-tuning performance. Then we propose a novel LoRA-based FedFT framework, termed LEGEND, which faces the difficulty of determining the number of LoRA layers (called, LoRA depth) and the rank of each LoRA layer (called, rank distribution). We analyze the coupled relationship between LoRA depth and rank distribution, and design an efficient LoRA configuration algorithm for heterogeneous devices, thereby promoting fine-tuning efficiency. Extensive experiments are conducted on a physical platform with 80 commercial devices. The results show that LEGEND can achieve a speedup of 1.5-2.8× and save communication costs by about 42.3% when achieving the target accuracy, compared to the advanced solutions.

To provide a flexible tradeoff between inference accuracy and resource requirement at runtime, the slimmable neural network (SNN), a single network executable at different widths with the same deploying and management cost as that of a single model, has been proposed. However, how to effectively train SNN among massive devices in edge computing without revealing their local data remains an open problem. To this end, we leverage a novel distributed machine learning paradigm, i.e., federated learning, to realize effective on-device SNN training. As current FL schemes often train only one model with fixed architecture, and the existing SNN training algorithm is resource-intensive, integrating FL and SNN is non-trivial. Furthermore, two intrinsic features in edge computing, i.e., data and system heterogeneity, exacerbate the difficulty. Motivated by this, we redesign the model distribution, local training, and model aggregation phases in traditional FL, and propose FedSNN, a framework that ensures all widths in SNN can obtain high accuracy with less resource consumption. Specifically, for devices with heterogeneous training capacities and data distributions, the parameter server will distribute each of them with one proper width for adaptive local training guided by their uploaded model features, and their trained models will be weighted-averaged using the proposed multi-width SNN aggregation to improve their statistical utility. Extensive experiments on a distributed testbed show that FedSNN improves the model accuracy by about 2.18%-8.1%, and accelerates training by about$1.31\times $-$6.84\times $, compared with existing solutions.

Federated learning (FL) has recently gained tremendous attention in edge computing and the Internet of Things, due to its capability of enabling clients to perform model training at the network edge or end devices (i.e., clients). However, these end devices are usually resource-constrained without the ability to train large-scale models. In order to accelerate the training of large-scale models on these devices, we incorporate Split Learning (SL) into Federated Learning (FL), and propose a novel FL framework, termedPairingFL. Specifically, we split a full model into a bottom model and a top model, and arrange participating clients into pairs, each of which collaboratively trains the two partial models as one client does in typical FL. Driven by the advantages of SL and FL, PairingFL is able to relax the computation burden on clients and protect model privacy. However, considering the features of system and statistical heterogeneity in edge networks, it is challenging to pair the clients by carefully developing the strategies of client partitioning and matching for efficient model training. To this end, we first theoretically analyze the convergence property of PairingFL, and obtain a convergence upper bound. Guided by this, we then design a greedy and efficient algorithm, which makes the joint decision of client partitioning and matching, so as to well balance the trade-off between convergence rate and model accuracy. The performance of PairingFL is evaluated through extensive simulation experiments. The experimental results demonstrate that PairingFL can speed up the training process by$4.6\times $compared to baselines when achieving the corresponding convergence accuracy.

Nowadays, federated learning (FL) has been widely adopted to train deep neural networks (DNNs) among massive devices without revealing their local data in edge computing (EC). To relieve the communication bottleneck of the central server in FL, hierarchical federated learning (HFL), which leverages edge servers as intermediaries to perform model aggregation among devices in proximity, comes into being. Nevertheless, the existing HFL systems may not perform training effectively due to bandwidth constraints and non-IID issues on devices. To conquer these challenges, we introduce anHFL system with device-edgeassignment andlayer selection, namely Heal. Specifically, Heal organizes all the devices into a hierarchical structure (i.e., device-edge assignment) and enables each device to forward only a sub-model with several valuable layers for aggregation (i.e., layer selection). This processing procedure is called layer-wise aggregation. To further save communication resource and improve the convergence performance, we then design an iteration-based algorithm to optimize the development of our layer-wise aggregation strategy by considering the data distribution as well as resource constraints among devices. Extensive experiments on both the physical platform and the simulated environment show that Heal accelerates DNN training by about 1.4–12.5×, and reduces the network traffic consumption by about 31.9–64.1%, compared with the existing HFL systems.

Federated learning (FL) has gained Important attention for training deep learning models across clients in edge computing. The scarcity of labeled data poses critical challenges in professional fields (e.g., medical diagnosis) for FL, motivating the development of federated semi-supervised learning (FSSL) to exploit unlabeled data. The existing works of FSSL always assign fixed values for global updating frequency and/or local updating frequency during training. Though the previous works can make full use of unlabeled data, they may still hinder the improvement of model performance on heterogeneous clients, due to that the two hyper-parameters are coupled and have a joint impact on training process. To this end, we propose a novel FSSL framework, named LOGO, to enhance training efficiency by jointly optimizing local and global updating frequencies. We analyze the coupled impact of these two hyper-parameters on model training. Then, we develop a multi-armed bandit (MAB) based online algorithm to adaptively determine diverse local updating frequencies for heterogeneous clients as well as appropriate global updating frequency, so as to address system heterogeneity and improve training efficiency. The performance of LOGO is evaluated through extensive simulation experiments. The experimental results demonstrate that LOGO achieves the model training speedup by 2.3 × and reduces communication cost by 44%, compared to the baselines.

Federated learning (FL) provides a distributed framework for multiple clients to collaboratively train models without exposing raw data. Most FL research assumes that all clients have fully labeled data, which is impractical for many real-world applications. To this end, we focus on semi-supervised FL (SSFL), where data samples of each client are partially labeled. However, existing SSFL methods ignore two inherent characteristics of FL: limited communication resources and heterogeneous data distribution, which severely hinder convergence stability and efficiency. This paper proposes a novel SSFL mechanism, called FedAC, to address the above two challenges by alternating client-to-client (C2C) collaboration. Specifically, we group all clients using different clustering strategies at two different training stages. During each global round, FedAC first performs similarity clustering based on local data distribution, which gathers the knowledge from similar clients to generate high-quality pseudo-labels for unlabeled data. Then the clients are re-grouped using dissimilarity clustering strategy to approximate the IID setting at the cluster level, thereby alleviating the bias induced by Non-IID data. FedAC adopts a reinforcement learning algorithm to achieve a balance between labeling assistance from similar clients and unbiased optimization from dissimilar clients. Extensive evaluations demonstrate that FedAC can improve model accuracy and save up to 59.65% of communication costs compared with existing benchmarks.

Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To boost the performance of AI applications, large-scale models have received increasing attention due to their excellent generalized abilities. However, training and transmitting large-scale models will incur significant computing and communication burden on the resource-constrained workers, and the exchange of entire models may violate model privacy. To relax the burden of workers and protect model privacy, split federated learning (SFL) has been released by integrating both data and model parallelism. Despite resource limitations, SFL also faces two other critical challenges in EC systems, i.e., statistical heterogeneity and system heterogeneity. In order to address these challenges, we propose a novel SFL framework, termed MergeSFL, by incorporating feature merging and batch size regulation in SFL. Concretely, feature merging aims to merge the features from workers into a mixed feature sequence, which is approximately equivalent to the features derived from IID data and is employed to promote model accuracy. While batch size regulation aims to assign diverse and suitable batch sizes for heterogeneous workers to improve training efficiency. Moreover, MergeSFL explores to jointly optimize these two strategies upon their coupled relationship to better enhance the performance of SFL. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson edge devices, and the experimental results show that MergeSFL can improve the final model accuracy by 5.82% to 26.22%, with a speedup by about 1.39x to 4.14x, compared to the baselines.

Recently, Hierarchical Federated Learning (HFL) stands out as a cutting-edge approach to efficiently learn knowledge from massive data on edge devices or clients. To alleviate the computation/communication burden of training large-scale models on resource-constrained clients, Hierarchical Split Federated Learning (HSFL), which splits an entire model into a top and bottom (sub-)model and offloads the training of the top model to the edge server, has been proposed. Nonetheless, there are two key issues, i.e., system heterogeneity and dynamic contexts, hindering the application of effective HSFL. In response, we present an efficient HSFL method, termed AdaHSFL, which introduces intra-cluster gradient feedback regulation and inter-cluster updating frequencies optimization to enhance training efficiency. Concretely, intra-cluster gradient feedback regulation enables edge servers to instantly process incoming smashed data and calculate gradients using top model copies on background threads, while inter-cluster updating frequencies optimization adjusts edge cluster updating frequencies to align the training duration across all clusters with that of the fastest cluster. Furthermore, AdaHSFL explores to jointly implement these two strategies to eliminate the idle waiting time both intra- and intercluster incurred by synchronization barriers. Rigorous performance evaluation demonstrates that AdaHSFL can improve the accuracy by $3.9 \%-25.5 \%$ within given time budgets, compared with the baselines.

Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS) and accelerate the training of large-scale models on resource-constraint workers in edge computing (EC) system, we propose a novel split federated learning (SFL) framework, termed ParallelSFL. Concretely, we split an entire model into a bottom submodel and a top submodel, and divide participating workers into multiple clusters, each of which collaboratively performs the SFL training procedure and exchanges entire models with the PS. However, considering the statistical and system heterogeneity in edge systems, it is challenging to arrange suitable workers to specific clusters for efficient model training. To address these challenges, we carefully develop an effective clustering strategy by optimizing a utility function related to training efficiency and model accuracy. Specifically, ParallelSFL partitions workers into different clusters under the heterogeneity restrictions, thereby promoting model accuracy as well as training efficiency. Meanwhile, ParallelSFL assigns diverse and appropriate local updating frequencies for each cluster to further address system heterogeneity. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson devices, and the experimental results show that ParallelSFL can reduce the traffic consumption by at least 21%, speed up the model training by at least 1.36X, and improve model accuracy by at least 5% in heterogeneous scenarios, compared to the baselines.

The emerging Federated Learning (FL) permits all workers (e.g., mobile devices) to cooperatively train a model using their local data at the network edge. In order to avoid the possible bottleneck of conventional parameter server architecture, the decentralized federated learning (DFL) is developed on the peer-to-peer (P2P) communication. In DFL, model exchanging among workers is usually regarded as an atomic operation, which largely affects the total bandwidth consumption during model training. Given the limited communication resource on workers, model exchanging will pose a great challenge when meeting with the large-scale models. Herein, we propose to let workers exchange theintermediate results, instead of the entire model, with each other. We provide theoretical analysis of DFL based on intermediate result exchanging, which reveals the relationship between the training performance and the exchanging interval (i.e., the number of local updating iterations) of intermediate results. According to the convergence bound, we propose an adaptive exchanging interval (or frequency) algorithm called Fed-IR, which optimizes the trade-off between communication cost and training performance. Extensive simulation results show that compared with the model exchanging methods, our proposed algorithms can save communication traffic of around 42%$\sim$81% while still achieving the similar accuracy.

The emerging Federated Learning (FL) permits all workers (e.g., mobile devices) to cooperatively train a model using their local data at the network edge. In order to avoid the possible bottleneck of conventional parameter server architecture, the decentralized federated learning (DFL) is developed on the peer-to-peer (P2P) communication. Non-IID issue is a key challenge in FL and will significantly degrade the model training performance. To this end, we propose a personalized solution called TOPFL, in which only parts of the local models (not the entire models) are shared and aggregated. Moreover, considering the limited communication bandwidth on workers, we propose a topology construction algorithm to accelerate the training process. To verify the convergence of the decentralized training framework, we theoretically analyze the impact of the data heterogeneity and topology on the convergence upper bound. Extensive simulation results show that TOPFL can achieve 2.2× speedup when reaching convergence and 5.8% higher test accuracy under the same resource consumption, compared with the baseline solutions.

The massive data from mobile and embedded devices have huge potential for training machine learning models. Decentralized machine learning (DML) can avoid the inherent bottleneck of the parameter server (PS) by collaboratively training models in a device-to-device (D2D) fashion. However, the previous DML works often assume that the local data are fully annotated with ground-truth labels, which is unrealistic for many Internet of Things (IoT) applications. This arises a new practical DML scenario, namely semi-supervised DML, where the local data of distributed workers are partially labeled in the D2D network. The existing semi-supervised learning techniques are proposed for standalone or the PS architecture, which ignore the impact of D2D topology on the performance of semi-supervised learning. Thus, they cannot adequately leverage the unlabeled data of decentralized workers, leading to performance degradation. Herein, we propose a novel framework, called SSD, to address the problem of semi-supervised DML by exploiting D2D cooperation. The key insight behind SSD is that neighbor selection has a crucial impact on pseudo-label quality and communication overhead. In SSD, each worker adaptively selects its neighbors with high-quality models and similar data distribution under communication resource constraints, which helps to generate high-confidence pseudo-labels for local unlabeled data and further boosts the DML performance. Extensive empirical evaluations on both testbed and simulated environments show that SSD significantly outperforms other baselines.

Federated learning (FL) has emerged as a promising distributed learning paradigm that enables a large number of mobile devices to cooperatively train a model without sharing their raw data. The iterative training process of FL incurs considerable computation and communication overhead. The workers participating in FL are usually heterogeneous and the workers with poor capabilities may become the bottleneck of model training. To address the challenges of resource overhead and system heterogeneity, this article proposes an efficient FL framework, called FedMP, that improves both computation and communication efficiency over heterogeneous workers through adaptive model pruning. We theoretically analyze the impact of pruning ratio on training performance, and employ a Multi-Armed Bandit based online learning algorithm to adaptively determine different pruning ratios for heterogeneous workers, even without any prior knowledge of their capabilities. As a result, each worker in FedMP can train and transmit the sub-model that fits its own capabilities, accelerating the training process without hurting model accuracy. To prevent the diverse structures of pruned models from affecting the training convergence, we further present a new parameter synchronization scheme, called Residual Recovery Synchronous Parallel (R2SP). Besides, our proposed framework can be extended to the peer-to-peer (P2P) setting. Extensive experiments on physical devices demonstrate that FedMP is effective for different heterogeneous scenarios and data distributions, and can provide up to 4.1× speedup compared to the existing FL methods.

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing (EC). Aided by EC, decentralized federated learning (DFL), which overcomes the single-point-of-failure problem in the parameter server based federated learning, is becoming a practical and popular approach for machine learning over distributed data. However, DFL faces two critical challenges,i.e., system heterogeneity and statistical heterogeneity introduced by edge devices. To ensure fast convergence with the existence of slow edge devices, we present an efficient DFL method, termed FedHP, which integrates adaptive control of both local updating frequency and network topology to better support the heterogeneous participants. We establish a theoretical relationship between local updating frequency and network topology regarding model training performance and obtain a convergence upper bound. Upon the convergence bound, we propose an optimization algorithm that adaptively determines local updating frequencies and constructs the network topology, so as to speed up convergence and improve the model accuracy. We evaluate the performance of FedHP through extensive simulation and testbed experiments. Evaluation results show that the proposed FedHP can reduce the completion time by about 51% and improve model accuracy by at least 5% in heterogeneous scenarios, compared with the baselines.

Federated learning (FL) has been widely adopted to train machine learning models over massive data in edge computing. Most works of FL employ pre-defined model architectures on all participating clients for model training. However, these pre-defined architectures may not be the optimal choice for the FL setting since manually designing a high-performance neural architecture is complicated and burdensome with intense human expertise and effort, which easily makes the model training fall into the local suboptimal solution. To this end, Neural Architecture Search (NAS) has been applied to FL to address this critical issue. Unfortunately, the search space of existing federated NAS approaches is extraordinarily large, resulting in unacceptable completion time on the resource-constrained edge clients, especially under the non-independent and identically distributed (non-IID) setting. In order to remedy this, we propose a novel framework, calledFinch, which adopts hierarchical neural architecture search to enhance federated learning. InFinch, we first divide the clients into several clusters according to the data distribution. Then, some subnets are sampled from a pre-trained supernet and allocated to the specific client clusters for searching the optimal model architecture in parallel, so as to significantly accelerate the process of model searching and training. The extensive experimental results demonstrate the high effectiveness of our proposed framework. Specifically,Finchcan reduce the completion time by about 30.6%, and achieve an average accuracy improvement of around 9.8% compared with the baselines.

Federated learning (FL) is an effective approach to train models collaboratively among distributed edge nodes (i.e., workers) while facing three crucial challenges, edge heterogeneity, resource constraint, and Non-IID data. Under the parameter server (PS) architecture, a single parameter server may become the system bottleneck and cannot well deal with the edge heterogeneity, while the peer-to-peer (P2P) architecture causes significant communication consumption to achieve satisfactory training performance. To this end, hierarchical aggregation (HA) architecture is proposed to cluster workers to tackle the edge heterogeneity and reduce communication consumption for FL. However, the existing researches on HA architecture cannot provide a unified clustering approach for various inter-cluster aggregation patterns (e.g., centralized or decentralized structure, synchronous or asynchronous mode). In this paper, we explore the quantitative relationship between the convergence bounds of different inter-cluster patterns and several factors, e.g., data distribution, frequency of clusters participating in inter-cluster aggregation (for asynchronous modes), and inter-cluster topology (for decentralized structures). Based on the convergence bounds, we design a unified clustering algorithm FedUC to organize workers for different patterns. Experimental results on classical models and datasets show that FedUC can greatly accelerate the model training of different patterns by 1.79-7.39× compared with the state-of-the-art clustering methods.

The emerging Personalized Federated Learning (PFL) methods aim to produce personalized models for different users, so as to keep track of their individualized requirements in Edge Computing (EC). The centralized PFL methods may suffer from the communication bottleneck and single point of failure. As an alternative solution, the decentralized PFL (DPFL) methods are performed in a Peer-to-Peer (P2P) manner, and collaboratively train personalized models by model aggregation among congenial devices. However, these DPFL methods may incur high communication cost and low resource utilization induced by large-scale models. Herein, we take the communication constraint and heterogeneity into consideration and propose to realize communication-efficient DPFL with adaptive model pruning and neighbor selection. We theoretically analyze the convergence of the proposed DPFL method, and study the impacts of both model pruning and neighbor selection on training performance. Furthermore, we propose an efficient algorithm that combines model pruning and neighbor selection to achieve a trade-off between model quality and communication cost. Extensive simulation and testbed experiments on real-world datasets are conducted. The experimental results demonstrate that the proposed algorithm can improve the test accuracy by at most 13% and save the traffic consumption by 45.4% on average compared with the existing PFL methods.

Federated learning (FL) has recently gained tremendous attention in edge computing and Internet of Things, due to its capability of enabling distributed clients to cooperatively train models while keeping raw data locally. However, the existing works usually suffer from limited communication resources, dynamic network conditions and heterogeneous client properties, which hinder efficient FL. To simultaneously tackle the above challenges, we propose a heterogeneity-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Specifically, FedCG introduces diversity to client selection and aims to select a representative client subset considering statistical heterogeneity. These selected clients are assigned different compression ratios based on heterogeneous and time-varying capabilities. After local training, they upload sparse model updates matching their capabilities for global aggregation, which can effectively reduce the communication cost and mitigate the straggler effect. More importantly, instead of naively combining client selection and gradient compression, we highlight that their decisions are tightly coupled and indicate the necessity of joint optimization. We theoretically analyze the impact of both client selection and gradient compression on convergence performance. Guided by the convergence rate, we develop an iteration-based algorithm to jointly optimize client selection and compression ratio decision using submodular maximization and linear programming. On this basis, we propose the quantized extension of FedCG, termed Q-FedCG, which further adjusts quantization levels based on gradient innovation. Extensive experiments on both real-world prototypes and simulations show that FedCG and its extension can provide up to 6.4× speedup.

Federated learning (FL) enables edge devices to cooperatively train models without exposing their raw data. However, implementing a practical FL system at the network edge mainly faces three challenges: label noise, data non-IIDness, and device heterogeneity, which seriously harm model performance and slow down convergence speed. Unfortunately, none of the existing works tackle all three challenges simultaneously. To this end, we develop a novel FL system, called Aorta, which features adaptive dataset construction and aggregation weightassignment. On each client, Aorta first calibrates potentially noisy labels and then constructs a training dataset with low noise, balanced distribution, and proper size. To fully utilize limited data on clients, we propose a global model guided method to select clean data and progressively correct noisy labels. To achieve balanced class distribution and proper dataset size, we propose a distribution-and-capability-aware data augmentation method to generate local training data. On the server, Aorta assigns aggregation weights based on the quality of local models to ensure that high-quality models have a greater influence on the global model. The model quality is measured through its cosine similarity with a benchmark model, which is trained on a clean and balanced dataset. We conduct extensive experiments on four datasets with various settings, including different noise types/ratios and non-IID types/levels. Compared to the baselines, Aorta improves model accuracy up to 9.8% on the datasets with moderate noise and non-IIDness, while providing a speedup of 4.2× on average when achieving the same target accuracy.

Federated Learning (FL) has been widely adopted to process the enormous data in the application scenarios like Edge Computing (EC). However, the commonly-used synchronous mechanism in FL may incur unacceptable waiting time for heterogeneous devices, leading to a great strain on the devices' constrained resources. In addition, the alternative asynchronous FL is known to suffer from the model staleness, which will lead to performance degradation of the trained model, especially onnon-i.i.d.data. In this paper, we design a novel asynchronous FL mechanism, named FedLC, to handle thenon-i.i.d.issue in EC by enabling the local collaboration among edge devices. Specifically, apart from uploading the local model directly to the server, each device will transmit its gradient to the other devices with different data distributions for local collaboration, which can improve the model generality. We theoretically analyze the convergence rate of FedLC and obtain the quantitative relationship between convergence bound and local collaboration. We design an efficient algorithm utilizing demand-list to determine the set of devices receiving gradients from each device. To handle the model staleness, we further assign different learning rates for various devices according to their participation frequency. The extensive experimental results demonstrate the effectiveness of our proposed mechanism.

Federated learning (FL) has been widely applied to collaboratively train deep learning (DL) models on massive end devices (i.e., clients). Due to the limited storage capacity and high labeling cost, the data on each client may be insufficient for model training. Conversely, in cloud datacenters, there exist large-scale unlabeled data, which are easy to collect from public access (e.g., social media). Herein, we propose theAda-FedSemisystem, which leverages both on-device labeled data and in-cloud unlabeled data to boost the performance of DL models. In each round, local models are aggregated to produce pseudo-labels for the unlabeled data, which are utilized to enhance the global model. Considering that the number of participating clients and the quality of pseudo-labels will have a significant impact on the training performance, we introduce a multi-armed bandit (MAB) based online algorithm to adaptively determine the participating fraction and confidence threshold. Besides, to alleviate the impact of stragglers, we assign local models of different depths for heterogeneous clients. Extensive experiments on benchmark models and datasets show that given the same resource budget, the model trained by Ada-FedSemi achieves 3%$\sim$14.8% higher test accuracy than that of the baseline methods. When achieving the same test accuracy, Ada-FedSemi saves up to 48% training cost, compared with the baselines. Under the scenario with heterogeneous clients, the proposed HeteroAda-FedSemi can further speed up the training process by$1.3\times \sim 1.5\times$.

Data generated at the network edge can be processed locally by leveraging the emerging technology of Federated Learning (FL). However, non-IID local data will lead to degradation of model accuracy and the heterogeneity of edge nodes inevitably slows down model training efficiency. Moreover, to avoid the potential communication bottleneck in the parameter-server-based FL, we concentrate on the Decentralized Federated Learning (DFL) that performs distributed model training in Peer-to-Peer (P2P) manner. To address these challenges, we propose an asynchronous DFL system by incorporating neighbor selection and gradient push, termed AsyDFL. Specifically, we require each edge node to push gradients only to a subset of neighbors for resource efficiency. Herein, we first give a theoretical convergence analysis of AsyDFL under the complicated non-IID and heterogeneous scenario, and further design a priority-based algorithm to dynamically select neighbors for each edge node so as to achieve the trade-off between communication cost and model performance. We evaluate the performance of AsyDFL through extensive experiments on a physical platform with 30 NVIDIA Jetson edge devices. Evaluation results show that AsyDFL can reduce the communication cost by 57% and the completion time by about 35% for achieving the same test accuracy, and improve model accuracy by at least 6% under the non-IID scenario, compared to the baselines.

Recently, edge AI has been launched to mine and discover valuable knowledge at network edge. Federated Learning, as an emerging technique for edge AI, has been widely deployed to collaboratively train models on many end devices in data-parallel fashion. To alleviate the computation/communication burden on the resource-constrained workers (e.g., end devices) and protect user privacy, Spilt Federated Learning (SFL), which integrates both data parallelism and model parallelism in Edge Computing (EC), is becoming a practical and popular approach for model training over distributed data. However, apart from the resource limitation, SFL still faces two other critical challenges in EC, i.e., system heterogeneity and context dynamics. To overcome these challenges, we present an efficient SFL method, named AdaSFL, which controls both local updating frequency and batch size to better accelerate model training. We theoretically analyze the model convergence rate and obtain a convergence upper bound regarding local updating frequency given a fixed batch size. Upon this, we develop a control algorithm to determine adaptive local updating frequency and diverse batch sizes for heterogeneous workers to enhance the training efficiency. The experimental results show that AdaSFL can reduce the completion time by about 43% and the network traffic consumption by about 31% for achieving the similar test accuracy, compared to the baselines.

To approach the challenges of non-IID data and limited communication resource raised by the emerging federated learning (FL) in mobile edge computing (MEC), we propose an efficient framework, calledFedMigr, which integrates a deep reinforcement learning (DRL) based model migration strategy into the pioneer FL algorithmFedAvg. According to the data distribution and resource budgets, ourFedMigrwill intelligently guide one client to forward its local model to another client after local updating, before directly sending the local models to the server for global aggregation as inFedAvg. Intuitively, migrating a local model from one client to another is equivalent to training the model over more data from different clients, alleviating the influence of non-IID issue. To this end, we propose an experience-driven method to make proper decisions for model migrations while satisfying the resource constraints. We also prove thatFedMigrcan help to reduce the parameter divergences between different local models and the global model from a theoretical perspective under the non-IID setting. Extensive experiments on three popular benchmark datasets demonstrate thatFedMigrcan achieve an average accuracy improvement of around 13%, and reduce bandwidth consumption for global communication by 42% on average, compared with the baselines.

Federated Learning (FL) is a distributed model training framework that allows multiple clients to collaborate on training a global model without disclosing their local data in edge computing (EC) environments. However, FL usually faces statistical heterogeneity (e.g., non-IID data) and system heterogeneity (e.g., computing and communication capabilities), resulting in poor model training performance. To deal with the above two challenges, we propose an efficient FL framework, named FedBR, which integrates the idea of block-wise regularization and knowledge distillation (KD) into the pioneering FL algorithm FedAvg, for resource-constrained edge computing. Specifically, we first divide the model into multiple blocks according to the layer order of deep neural network (DNN). The server only sends some consecutive model blocks instead of an entire model to clients for communication efficiency. Then, the clients make use of knowledge distillation to absorb the knowledge of global model blocks to alleviate statistical heterogeneity during local training. We provide a theoretical convergence guarantee for FedBR and show that the convergence bound will decrease as the increasing number of model blocks sent by the server. Besides, since the increasing number of model blocks brings more computing and communication costs, we design a heuristic algorithm (GMBS) to determine the appropriate number of model blocks for clients according to their varied data distributions, computing, and communication capabilities. Extensive experimental results show that FedBR can reduce the bandwidth consumption by about 31%, and achieve an average accuracy improvement of around 5.6% compared with the baselines under heterogeneous settings.

At the network edge, federated learning (FL) has gained attention as a promising approach for training deep learning (DL) models collaboratively across a large number of devices while preserving user privacy. However, FL still faces specific challenges related to the limited, heterogeneous and dynamic resources of devices. In most FL systems, all devices train the same model, while the devices with constrained resources, referred to as stragglers, will significantly slow down overall training process. It is intuitive to alleviate computation and communication load on the stragglers by training and transmitting a part of the model. Inspired by multi-exit models, we divide an original DL model into several non-overlapping blocks, which can be trained separately on the low-capability devices. Furthermore, we propose BOSE, a novel FL system that performs adaptiveblock-wisemodel training under resource constraints. Considering the diverse impacts of different blocks on model convergence and the varying training loads they incur, a naive block assignment strategy, e.g., uniformly random assignment, may not yield optimal model performance and fail to fully utilize available resources. To this end, we introduce two metrics, includinglearning speedanddevice-wise divergence, to measure the potential of blocks in promoting model convergence. Given resource budget, BOSE initially identifies a set of candidate blocks for each device and subsequently selects specific training blocks based on their potential for promoting model convergence. In general, blocks with higher potential are more likely to be chosen for training. Extensive experiments on a physical platform show that BOSE provides a 1.4$\times$$\sim$3.8$\times$speedup without sacrificing model accuracy, compared to the baselines.

The emerging paradigm of federated learning (FL) strives to enable devices to cooperatively train models without exposing their raw data. In most cases, the data across devices are non-independently and identically distributed in FL. Thus, the local models trained over different data distributions will inevitably deviate from the global optima, which induces optimization inconsistency and even hurts global convergence. Moreover, the resource-constrained devices with heterogeneous training capacities (e.g., computing and communication) further slow down the convergence rate. To this end, we introduce anFL framework withadaptive datasampling and localtraining, namely FAST. Specifically, even without devices’ private data distributions, FAST enables each device to sample different rates of data points from each of its local classes to rebuild a dataset for training, thus adjusting the convergence direction of the aggregated global model to be closer to the global optima. The theoretical analysis shows that the convergence bound depends on the sampling rates as well as the number of local iterations executed on the sampled data. To achieve resource-effective and convergence-guaranteed FL, we then design an online learning algorithm that jointly optimizes the data sampling and local training strategies so as to encourage the decrease of global loss under the given time budget. Extensive experiments on physical and simulated environments show that, FAST improves the model accuracy by about 1.55%-6.78% given the same time budget, and accelerates training by about 1.39-5.89× with the same target accuracy, compared with the baselines.

Data generated at the network edge can be processed locally by leveraging the emerging technology of Federated Learning (FL). However, non-IID local data will lead to degradation of model accuracy and the heterogeneity of edge nodes inevitably slows down model training efficiency. Moreover, to avoid the potential communication bottleneck in the parameter-server-based FL, we concentrate on the Decentralized Federated Learning (DFL) that performs distributed model training in Peer-to-Peer (P2P) manner. To address these challenges, we propose an asynchronous DFL system by incorporating neighbor selection and gradient push, termed AsyNG. Specifically, we require each edge node to push gradients only to a subset of neighbors for resource efficiency. Herein, we first give a theoretical convergence analysis of AsyNG under the complicated non-IID and heterogeneous scenario, and further design a priority-based algorithm to dynamically select neighbors for each edge node so as to achieve the trade-off between communication cost and model performance. We evaluate the performance of AsyNG through extensive experiments on a physical platform. Evaluation results show that AsyNG can reduce the communication cost by 60% and the completion time by about 30% for achieving the same test accuracy, compared to the baselines.

Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, dynamic network conditions and heterogeneous client properties, which slow down the convergence of FL. To tackle the above challenges, we propose a heterogeneity-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Specifically, the parameter server (PS) selects a representative client subset considering statistical heterogeneity and sends the global model to them. After local training, these selected clients upload compressed model updates matching their capabilities to the PS for aggregation, which significantly alleviates the communication load and mitigates the straggler effect. We theoretically analyze the impact of both client selection and gradient compression on convergence performance. Guided by the derived convergence rate, we develop an iteration-based algorithm to jointly optimize client selection and compression ratio decision using submodular maximization and linear programming. Extensive experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3× speedup compared to other methods.

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing (EC). Aided by EC, decentralized federated learning (DFL), which overcomes the single-point-of-failure problem in the parameter server (PS) based federated learning, is becoming a practical and popular approach for machine learning over distributed data. However, DFL faces two critical challenges, i.e., system heterogeneity and statistical heterogeneity introduced by edge devices. To ensure fast convergence with the existence of slow edge devices, we present an efficient DFL method, termed FedHP, which integrates adaptive control of both local updating frequency and network topology to better support the heterogeneous participants. We establish a theoretical relationship between local updating frequency and network topology regarding model training performance and obtain a convergence upper bound. Upon this, we propose an optimization algorithm, that adaptively determines local updating frequencies and constructs the network topology, so as to speed up convergence and improve the model accuracy. Evaluation results show that the proposed FedHP can reduce the completion time by about 51% and improve model accuracy by at least 5% in heterogeneous scenarios, compared with the baselines.

Federated Learning (FL) has emerged as an efficient distributed model training framework that enables multiple clients cooperatively to train a global model without exposing their local data in edge computing (EC). However, FL usually faces statistical heterogeneity (e.g., non-IID data) and system heterogeneity (e.g., computing and communication capabilities), resulting in poor model training performance. To deal with the above two challenges, we propose an efficient FL framework, named FedBR, which integrates the idea of block-wise regularization and knowledge distillation (KD) into the pioneer FL algorithm FedAvg, for resource-constrained edge computing. Besides, we design a heuristic algorithm (GMBS) to determine the appropriate number of model blocks for clients according to their varied data distributions, computing, and communication capabilities. Extensive experimental results show that FedBR can reduce the time cost by 19.5% and the communication cost by 27% on average compared with the other three baselines when achieving the target testing accuracy under heterogeneous settings.

Falling is a common health problem for elderly people. Early detection of falls allows earlier rescue measures to be implemented. Most existing Wi-Fi-based fall detection systems employ learning-based methods, which require large amounts of labeled data for prior training. To address this issue, we in this paper present AFall, a robust model-based fall detection system that does not require prior training for a single person based on Wi-Fi Channel State Information (CSI). Different from previous Wi-Fi-based fall detection systems, we model the relationship between human falls and changes of Angle of Arrival (AoA) of Wi-Fi signals reflected from human body by multiple signal classification (MUSIC) algorithm. In particular, we deploy two receivers in orthogonal spatial layouts to capture diversified AoA information. Since AoA reflected from human body is independent of environments and subjects, the performance of AFall can remain stable when the environment changes slightly, which can meet the daily needs of the elderly people. We implement AFall using commodity Wi-Fi devices and evaluate it in five different indoor environments. The experimental results demonstrate that AFall achieves an average accuracy of 84.31% and an average F1 score of 84.56%.

Federated learning (FL) has been widely adopted to train machine learning models over massive data in edge computing. However, machine learning faces critical challenges, e.g., data imbalance, edge dynamics, and resource constraints, in edge computing. The existing FL solutions cannot well cope with data imbalance or edge dynamics, and may cause high resource cost. In this paper, we propose an adaptive asynchronous federated learning (AAFL) mechanism. To deal with edge dynamics, a certain fraction$\alpha$of all local updates will be aggregated by their arrival order at the parameter server in each epoch. Moreover, the system can intelligently vary the number of local updated models for global model aggregation in different epochs with network situations. We then propose experience-driven algorithms based on deep reinforcement learning (DRL) to adaptively determine the optimal value of$\alpha$in each epoch for two cases of AAFL, single learning task and multiple learning tasks, so as to achieve less completion time of training under resource constraints. Extensive experiments on the classical models and datasets show high effectiveness of the proposed algorithms. Specifically, AAFL can reduce the completion time by about 70 percent and improve the learning accuracy by about 28 percent under resource constraints, compared with the state-of-the-art solutions.

The emerging Federated Learning (FL) enables IoT devices to collaboratively learn a shared model based on their local datasets. However, due to end devices’ heterogeneity, it will magnify the inherent synchronization barrier issue of FL and result in non-negligible waiting time when local models are trained with the identical batch size. Moreover, the useless waiting time will further lead to a great strain on devices’ limited battery life. Herein, we aim to alleviate the negative impact of synchronization barrier through adaptive batch size during model training. When using different batch sizes, stability and convergence of the global model should be enforced by assigning appropriate learning rates on different devices. Therefore, we first study the relationship between batch size and learning rate, and formulate a scaling rule to guide the setting of learning rate in terms of batch size. Then we theoretically analyze the convergence rate of global model and obtain a convergence upper bound. On these bases, we propose an efficient algorithm that adaptively adjusts batch size with scaled learning rate for heterogeneous devices to reduce the waiting time and save battery life. We conduct extensive simulations and testbed experiments, and the experimental results demonstrate the effectiveness of our method.

Federated learning (FL) has emerged in edge computing to address the limited bandwidth and privacy concerns of traditional cloud-based training. However, the existing FL mechanisms may lead to a long training time and consume massive communication resources. In this paper, we propose an efficient FL mechanism, namely FedCH, to accelerate FL in heterogeneous edge computing. Different from existing works which adopt the pre-defined system architecture and train models in a synchronous or asynchronous manner, FedCH will construct a special cluster topology and perform hierarchical aggregation for training. Specifically, FedCH arranges all clients into multiple clusters based on their heterogeneous training capacities. The clients in one cluster synchronously forward their local updates to the cluster header for aggregation, while all cluster headers take the asynchronous method for global aggregation. Our analysis shows that the convergence bound depends on the number of clusters and the training epochs. We propose efficient algorithms to determine the optimal number of clusters with resource budgets and then construct the cluster topology to address the client heterogeneity. Extensive experiments on both physical platform and simulated environment show that FedCH reduces the completion time by 49.5-79.5% and the network traffic by 57.4-80.8%, compared with the existing FL mechanisms.

In edge computing (EC), federated learning (FL) enables massive devices to collaboratively train AI models without exposing local data. In order to avoid the possible bottleneck of the parameter server (PS) architecture, we concentrate on the decentralized federated learning (DFL), which adopts peer-to-peer (P2P) communication without maintaining a global model. However, due to the intrinsic features of EC, e.g., resource limitation and heterogeneity, network dynamics and non-IID data, DFL with a fixed P2P topology and/or an identical model compression ratio for all workers results in a slow convergence rate. In this paper, we propose an efficient algorithm (termed CoCo) to accelerate DFL by integrating optimization of topology Construction and model Compression. Concretely, we adaptively construct P2P topology and determine specific compression ratios for each worker to conquer the system dynamics and heterogeneity under bandwidth constraints. To reflect how the non-IID data influence the consistency of local models in DFL, we introduce the consensus distance, i.e., the discrepancy between local models, as the quantitative metric to guide the fine-grained operations of the joint optimization. Extensive simulation results show that CoCo achieves 10× speedup, and reduces the communication cost by about 50% on average, compared with the existing DFL baselines.

Data generated at the network edge can be processed locally by leveraging the paradigm of Edge Computing (EC). Aided by EC, Federated Learning (FL) has been becoming a practical and popular approach for distributed machine learning over locally distributed data. However, FL faces three critical challenges, i.e., resource constraint, system heterogeneity and context dynamics in EC. To address these challenges, we present a training-efficient FL method, termedFedLamp, by optimizing both theLocal updating frequency andmodel compression ratio in the resource-constrained EC systems. We theoretically analyze the model convergence rate and obtain a convergence upper bound related to the local updating frequency and model compression ratio. Upon the convergence bound, we propose a control algorithm, that adaptively determines diverse and appropriate local updating frequencies and model compression ratios for different edge nodes, so as to reduce the waiting time and enhance the training efficiency. We evaluate the performance ofFedLampthrough extensive simulation and testbed experiments. Evaluation results show thatFedLampcan reduce the traffic consumption by 63% and the completion time by about 52% for achieving the similar test accuracy, compared to the baselines.

Smartphones have been the necessities for us due to their advanced computing capabilities and ubiquitous connectivity to our daily lives. However, they also produce many negative influences, such as ring noise, nuisance calls, which interrupt people’s attention when working. It would be user-friendly if smartphones can automatically sense the surroundings and dynamically work at an appropriate profile to prevent their ringing from disturbing people in some special circumstances. To address this issue, in this paper, we propose a novel smartphone profile switching system, called AutoProfile, which combines the techniques of acoustic sensing, walk detection and machine learning to automatically and dynamically change smartphones’ profiles in different scenarios. We develop a new compact ambient sound scheme for feature extraction, named DWT & MFCC fingerprint, which can effectively distinguish between different social scenarios and outperforms the existing method. To evaluate the performance of AutoProfile, we conduct experiments in 8 scenarios and take multiple influence factors into consideration. The results demonstrate that AutoProfile can realize overall recognition accuracies of$91.4 \;\%$and$90.6 \;\%$when using Random Forest and$k$-nearest Neighbors classifiers, respectively. Moreover, since AutoProfile senses the ambient sound passively, it does not create additional noise compared with some active acoustic sensing schemes. In addition, the power consumption of AutoProfile is acceptable, and thus AutoProfile can be tailored as a background service of smartphones to make them become “smarter”.

Recently, mobile and embedded devices worldwide generate a massive amount of data at the network edge. To efficiently exploit the data from distributed devices, we concentrate on decentralized machine learning (DML), where the workers collaboratively train models under the peer-to-peer (P2P) setting. DML avoids the bottleneck of the parameter server (PS) by enabling the workers to exchange local models with their neighbors rather than the PS. However, DML still faces some key challenges, i.e., resource limitation, system heterogeneity, network dynamics and non-IID data. In this article, we design and implement MOTOR, an efficient DML mechanism that simultaneously addresses these challenges by applying model pruning and topology construction, thus accelerating DML. Specifically, MOTOR assigns different pruning ratios to heterogeneous workers. After model pruning, each worker will train and transmit a sub-model that fits its capabilities, reducing both computation and communication overhead. Besides, MOTOR dynamically constructs the network topology considering the time-varying network conditions and non-IID data distributions. We theoretically analyze the impact of pruning ratio and network topology on model training performance. Guided by the theoretical analysis, we develop a joint optimization algorithm for pruning ratio decision and topology construction to achieve the trade-off between resource overhead and training performance. We implement MOTOR on commercial devices and evaluate the performance with different DML tasks. Extensive experiments show that MOTOR achieves up to 4.2× speedup compared to the existing DML approaches.

Federated learning (FL) has been widely adopted to train machine learning models over massive distributed data sources in edge computing. However, the existing FL frameworks usually suffer from the difficulties of resource limitation and edge heterogeneity. Herein, we design and implement FedMP, an efficient FL framework through adaptive model pruning. We theoretically analyze the impact of pruning ratio on model training performance, and propose to employ a Multi-Armed Bandit based online learning algorithm to adaptively determine different pruning ratios for heterogeneous edge nodes, even without any prior knowledge of their computation and communication capabilities. With adaptive model pruning, FedMP can not only reduce resource consumption but also achieve promising accuracy. To prevent the diverse structures of pruned models from affecting the training convergence, we further present a new parameter synchronization scheme, called Residual Recovery Synchronous Parallel (R2SP), and provide a theoretical convergence guarantee. Extensive experiments on the classical models and datasets demonstrate that FedMP is effective for different heterogeneous scenarios and data distributions, and can provide up to 4.1× speedup compared to the existing FL methods.

To approach the challenges of non-IID data and limited communication resource raised by the emerging federated learning (FL) in mobile edge computing (MEC), we propose an efficient framework, called FedMigr, which integrates a deep reinforcement learning (DRL) based model migration strategy into the pioneer FL algorithm FedAvg. According to the data distribution and resource constraints, our FedMigr will intelligently guide one client to forward its local model to another client after local updating, rather than directly sending the local models to the server for global aggregation as in FedAvg. Intuitively, migrating a local model from one client to another is equivalent to training it over more data from different clients, contributing to alleviating the influence of non-IID issue. We prove that FedMigr can help to reduce the parameter divergences between different local models and the global model from a theoretical perspective, even over local datasets with non-IID settings. Extensive experiments on three popular benchmark datasets demonstrate that FedMigr can achieve an average accuracy improvement of around 13%, and reduce bandwidth consumption for global communication by 42% on average, compared with the baselines.

Federated learning (FL) has been widely applied to collaboratively train deep learning (DL) models on massive end devices (i.e., clients). Due to the limited storage capacity and high labeling cost, there are always insufficient data stored and annotated on each client. Conversely, in cloud datacenters, there exist large-scale unlabeled data, which are easy to collect from public access (e.g., social media). Herein, upon the federated semi-supervised learning (FSSL) technology, we propose the Ada-FedSemi system, which leverages both on-device labeled data and in-cloud unlabeled data to boost the performance of DL models. Given the limited communication and massive quantity of the clients, in each training round, we decide to select partial clients to participate in FL, and their local models are aggregated by the parameter server (PS) to produce pseudo-labels for the unlabeled data, which are utilized to enhance the global model. Considering that the number of participating clients and the quality of pseudo-labels will have a significant impact on the training performance (e.g., efficiency and accuracy), we introduce a multi-armed bandit (MAB) based online algorithm to adaptively determine the participating fraction and confidence threshold during federated model training. Extensive experiments on benchmark models and datasets show that, given the same resource budget, the model trained by Ada-FedSemi achieves 3%-14.8 % higher test accuracy than that of the baseline methods. Besides, when achieving the same test accuracy, Ada-FedSemi saves up to 48% training cost, compared with the baselines.

In edge computing (EC), federated learning (FL) has been widely used to cooperatively train machine learning models and protect privacy over the traditional approaches. In order to avoid the possible communication bottleneck and single point failure in parameter server (PS) framework, we mainly focus on decentralized federated learning (DFL) in which each worker disseminates information through peer-to-peer (P2P) communication network. However, the high communication cost and the non-IID local data hinder the efficient training of DFL. In this paper, we propose a mechanism (termed DFL-DF) to achieve efficient communication and improve the performance on non-IID data. Specifically, each worker will exchange data features with neighbors rather than models (or gradients). Different from the traditional fixed topology methods, each worker will communicate with its neighbors selected at each round. Extensive experiment results show the high effectiveness of DFL-DF. Specifically, DFL-DF can reduce communication cost by 29.4%-82.06% and improve test accuracy 2.5%-9.1% under communication cost constraints, compared with the traditional model exchanging methods.

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing. To fully utilize the widely distributed data, we concentrate on a wireless edge computing system that conducts model training using decentralized peer-to-peer (P2P) methods. However, there are two major challenges on the way towards efficient P2P model training: limited resources (e.g., network bandwidth and battery life of mobile devices) and time-varying network connectivity due to device mobility or wireless channel dynamics, which receives less attention in recent years. To address these two challenges, this paper studies the impact of topology construction on the P2P training performance. Specifically, we dynamically construct an efficient P2P topology, where model aggregation occurs at the edge. In a nutshell, we first formulate the topology construction for P2P learning (TCPL) problem with resource constraints as an integer programming problem. Then a learning-driven method is proposed to adaptively construct a topology at each training epoch. We evaluate the performance of our proposed algorithm through extensive simulations and physical platform. Evaluation results show that our method can improve the model training efficiency by about 11% with resource constraints, reduce the communication cost by 30% and the network traffic consumption by about 60% under the same accuracy requirement compared to the benchmarks.

Under the paradigm of edge computing, the enormous data generated at the network edge can be processed locally. To make full utilization of these widely distributed data, we focus on an edge computing system that conducts distributed machine learning using gradient-descent based approaches. To ensure the system’s performance, there are two major challenges: how to collect data from multiple data source nodes for training jobs and how to allocate the limited resources on each edge server among these jobs. In this paper, we jointly consider the two challenges for distributed training (without service requirement), aiming to maximize the system throughput while ensuring the system’s quality of service (QoS). Specifically, we formulate the joint problem as a mixed-integer non-linear program, which is NP-hard, and propose an efficient approximation algorithm. Furthermore, we take service placement into consideration for diverse training jobs and propose an approximation algorithm. We also analyze that our proposed algorithm can achieve the constant bipartite approximation under many practical situations. We build a test-bed to evaluate the effectiveness of our proposed algorithm in a practical scenario. Extensive simulation results and testing results show that the proposed algorithms can improve the system throughput 56-69 percent compared with the conventional algorithms.

Most existing Wi-Fi-based gait recognition systems consider gait cycle detection as a critical process. However, the noise mixed in dynamic measurements obtained from commercial Wi-Fi devices makes it hard to detect gait cycles. Herein, we adopt the attention-based Recurrent Neural Network (RNN) encoder-decoder and propose a cycle-independent human gait recognition and walking direction estimation system, termed AGait, in Wi-Fi networks. For capturing more human walking dynamics, two receivers together with one transmitter are deployed in different spatial layouts. The Channel State Information (CSI) from different receivers are first assembled and refined to form an integrated walking profile. Then, the RNN encoder reads and encodes the walking profile into primary feature vectors. Given a specific gait or direction sensing task, a corresponding and particular attention vector is computed by the decoder and is finally used to predict the target. The attention scheme motivates AGait to learn to adaptively align with different critical clips of CSI data for different tasks. We implement AGait on commercial Wi-Fi devices in three different indoor environments, and the experimental results demonstrate that AGait can achieve average$F_1$scores of 97.32 to 89.77 percent for gait recognition from a group of 4 to 10 subjects and 97.41 percent for direction estimation from 8 walking directions.

Human activity recognition is an essential part of human-computer interaction systems. Environment-robust Wi-Fi-based systems for this task is still a challenging problem, due to the fact that most existing systems may drop in performance when the environment is changed. To address this issue, we in this paper present WiHARAN, a Wi-Fi-based activity recognition system that can learn environment-independent features from Channel State Information (CSI) traces. With a well-designed base network capable of extracting temporal information from spectrograms, we align the joint distribution of features and labels from multiple environments utilizing adversarial learning. Experimental results show that our system achieves better performance than state-of-the-art solutions and can improve performance in difficult environments.

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing. To fully utilize the widely distributed data, we concentrate on a wireless edge computing system that conducts model training using decentralized peer-to-peer (P2P) methods. However, there are two major challenges on the way towards efficient P2P model training: limited resources (e.g., network bandwidth and battery life of mobile edge devices) and time-varying network connectivity due to device mobility or wireless channel dynamics, which have received less attention in recent years. To address these two challenges, this paper adaptively constructs a dynamic and efficient P2P topology, where model aggregation occurs at the edge devices. In a nutshell, we first formulate the topology construction for P2P learning (TCPL) problem with resource constraints as an integer programming problem. Then a learning-driven method is proposed to adaptively construct a topology at each training epoch. We further give the convergence analysis on training machine learning models even with non-convex loss functions. Extensive simulation results show that our proposed method can improve the model training efficiency by about 11% with resource constraints and reduce the communication cost by about 30% under the same accuracy requirement compared to the benchmarks.

Federated learning (FL) involves training machine learning models over distributed edge nodes (i.e., workers) while facing three critical challenges, edge heterogeneity, Non-IID data and communication resource constraint. In the synchronous FL, the parameter server has to wait for the slowest workers, leading to significant waiting time due to edge heterogeneity. Though asynchronous FL can well tackle the edge heterogeneity, it requires frequent model transfers, resulting in massive communication resource consumption. Moreover, the different relative frequency of workers participating in asynchronous updating may seriously hurt training accuracy, especially on Non-IID data. In this paper, we propose a semi-asynchronous federated learning mechanism (FedSA), where the parameter server aggregates a certain number of local models by their arrival order in each round. We theoretically analyze the quantitative relationship between the convergence bound of FedSA and different factors,e.g., the number of participating workers in each round, the degree of data Non-IID and edge heterogeneity. Based on the convergence bound, we present an efficient algorithm to determine the number of participating workers to minimize the training completion time. To further improve the training accuracy on Non-IID data, FedSA deploys adaptive learning rates for workers by their relative participation frequency. We extend our proposed mechanism to the dynamic and multiple learning tasks scenarios. Experimental results on the testbed show that our proposed mechanism and algorithms address the three challenges more effectively than the state-of-the-art solutions.

Traditional word embedding approaches learn semantic information at word level while ignoring the meaningful internal structures of words like morphemes.Furthermore, existing morphology-based models directly incorporate morphemes to train word embeddings, but still neglect the latent meanings of morphemes.In this paper, we explore to employ the latent meanings of morphological compositions of words to train and enhance word embeddings.Based on this purpose, we propose three Latent Meaning Models (LMMs), named LMM-A, LMM-S and LMM-M respectively, which adopt different strategies to incorporate the latent meanings of morphemes during the training process.Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models.The results demonstrate that our models outperform the baselines on five word similarity datasets.On Wordsim-353 and RG-65 datasets, our models nearly achieve 5% and 7% gains over the classic CBOW model, respectively.For the syntactic analogy and text classification tasks, our models also surpass all the baselines including a morphology-based model.

For online conversations with top privacy, we often need to erase the existing contact behavior. Thus we want communications in which adversaries can not link you to the person you contact, namely communications with unlinkability. However, most current communication systems including variations of Mix networks fail to maintain unlinkability against global active adversaries (GAA) who can monitor global traffic and easily compromise clients and infrastructures. Therefore, designing an unlinkable communication system against GAA is challenging. By analyzing limitations of current communication systems, we propose two other features to assure unlinkability: covertness and deniability. In this paper, we design HTor, a novel and practical communication system with unlinkability, via a single web server. HTor interpolates the server to cut off the direct connection between two people in one communication and exploits covert channels (CCs) to hide communications between clients and the server. Considering servers might be corrupted, HTor utilizes a group mechanism to protect the receiver for each message. By extensive large-scale evaluations, we show that communications over HTor are robust and difficult to detect. Besides, HTor is easily implemented and, with multiple servers, it can provide enough bandwidth and relatively low latency for chatting.

In recent literatures, WiFi signals have been widely used to "sense" people's locations and activities. Researchers have exploited the characteristics of wireless signals to "hear" people's talk and "see" keystrokes by human users. Inspired by the excellent work of relevant scholars, we turn to explore the field of human-computer interaction using finger-grained gestures under WiFi environment. In this paper, we present Wi-Finger - the first solution using ubiquitous wireless signals to achieve number text input in WiFi devices. We implement a prototype of WiFinger on a commercial Wi-Fi infrastructure. Our scheme is based on the key intuition that while performing a certain gesture, the fingers of a user move in a unique formation and direction and thus generate a unique pattern in the time series of Channel State Information (CSI) values. WiFinger is deigned to recognize a set of finger-grained gestures, which are further used to realize continuous text input in off-the-shelf WiFi devices. As the results show, WiFinger achieves up to 90.4% average classification accuracy for recognizing 9 digits finger-grained gestures from American Sign Language (ASL), and its average accuracy for single individual number text input in desktop reaches 82.67% within 90 digits.