Federated Learning (FL) enables knowledge sharing across client models with privacy preservation. A key challenge in FL is to aggregate general knowledge across clients while preserving personalized knowledge for each client. We discover that this challenge primarily stems from the coupling of general and personalized knowledge across different model layers. Existing methods either fail to fully decouple these two types of knowledge or do not leverage them effectively for inference, leading to suboptimal performance. This paper presents Thorki, a new FL system that decouples general and personalized knowledge throughout all model layers. In Thorki, instead of one model, each client stores its personalized knowledge in a small model and general knowledge in a large model. When making an inference, it employs a fusion network to combine the outputs of the two models, leveraging both types of knowledge adaptively. This new model collaboration paradigm allows clients to share their general knowledge in a federated manner without compromising their personalized inference capabilities. Extensive experiments with three models on four datasets demonstrate that Thorki outperforms state-of-the-art FL systems by 0.16%-19.14% in model accuracy and improves time-to-accuracy performance by 2.00x-10.00x.

Pre-trained visual models have been deployed on various edge devices to facilitate a broad range of downstream tasks through few-shot learning (FSL), in particular when downstream data or on-device resources are limited. However, FSL often suffers from poor performance due to its inability to adapt to the characteristics of the deployment environments, while backbone fine-tuning prior to model deployment is typically infeasible because of the unavailability of environment-specific samples. To tackle this challenge, this paper presents Glasses, a lightweight fine-tuning scheme that can adapt ViT-based model backbones to deployment environments rapidly through device-cloud collaboration, helping the model achieve better FSL performance on the device. Glasses leverages the computational power and sample resources in the cloud to produce model updates for rapid model adaptation based on only one environment image without needing a label. Experiments with five models on two datasets demonstrate that Glasses can adapt a model rapidly and outperform the original backbone by 5.54%–22.56% in the 1-shot setting and by 2.50%–10.28% in the 5-shot setting. The source code is available at https://github.com/CGCL-codes/Glasses.

In an edge-assisted federated learning (FL) system, edge servers aggregate the local models from the clients within their coverage areas to produce intermediate models for the production of the global model. This significantly reduces the communication overhead incurred during the FL process. To accelerate model convergence, FedEdge, the state-of-the-art edge-assisted FL system, trains clients' models in local federations when they wait for the global model in each training round. However, our investigation reveals that it drives the global model towards clients with excessive local training, causing model drifts that undermine model performance for other clients. To tackle this problem, this paper presents Maverick, a new edge-assisted FL system that mitigates model drifts by training personalized local models for clients through contrastive local training. It introduces a model-contrastive loss to facilitate personalized local federated training by driving clients' local models away from the global model and close to their corresponding intermediate models. In addition, Maverick includes anomalous models in contrastive local training as negative samples to accelerate the convergence of clients' local models. Extensive experiments are conducted on three widely-used models trained on three datasets to comprehensively evaluate the performance of Maverick. Compared to state-of-the-art edge-assisted FL systems, Maverick accelerates model convergence by up to 16.2x and improves model accuracy by up to 12.7%.

Machine learning (ML) models are widely deployed on edge nodes, such as mobile phones and edge servers, to power a wide range of AI applications over the web. Ensuring the integrity of these edge models is paramount, as they are subject to corruption caused by software/hardware exceptions and malicious tampering, which may undermine model performance, incur economic losses, and pose health risks. Existing data integrity mechanisms designed for files stored on disks cannot properly verify the integrity of models running in GPUs or mitigate the new integrity threats against edge models. This paper proposes EdgeThemis, a novel mechanism for verifying the integrity of edge models through sentinel verification. To enable verifiability for a model M, EdgeThemis embeds a sentinel backdoor and a verification module into M. Then, a challenger can send verification requests to the edge node hosting M to verify its integrity. Next, the sentinel activates the verification module to generate a unique integrity proof tied to the identity of the edge node for verification. Finally, the challenger can verify the integrity proof to detect model corruption. Theoretical analysis proves that EdgeThemis can properly mitigate potential integrity threats against edge models. Experiments demonstrate that EdgeThemis achieves a verification accuracy of 100.00% across various models and different types of model corruption with robustness against replay attacks, theft attacks, and replacement attacks.

In an edge storage system, popular data can be stored on edge servers to enable low-latency data retrieval for nearby users. Suffering from constrained storage capacities, edge servers must process users' data requests collaboratively. For sourcing data, it is essential to find out which edge servers in the system have the requested data. In this paper, we make the first attempt to study this edge data query (EDQ) problem and present EDIndex, a distributed Edge Data Indexing system to enable fast data queries at the edge. First, we introduce a new index structure named Counting Bloom Filter (CBF) tree for facilitating edge data queries. Then, to improve query performance, we enhance EDIndex with a novel index structure named hierarchical Counting Bloom Filter (HCBF) tree. In EDIndex, each edge server maintains an HCBF tree that indexes the data stored on nearby edge servers to facilitate data sourcing between edge servers at the edge. The results of extensive experiments conducted on an edge storage system comprised of 90 edge servers demonstrate that EDIndex 1) takes up to 8.8x less time to answer edge data queries compared with state-of-the-art edge indexing systems; and 2) can be implemented in practice with a high query accuracy at low initialization and maintenance overheads.

Training machine learning (ML) models on mobile and Web-of-Things (WoT) has been widely acknowledged and employed as a promising solution to privacy-preserving ML. However, these end-devices often suffer from constrained resources and fail to accommodate increasingly large ML models that crave great computation power. Offloading ML models partially to the cloud for training strikes a trade-off between privacy preservation and resource requirements. However, device-cloud training creates communication overheads that delay model training tremendously. This paper presents EdgeMove, the first device-edge training scheme that enables fast pipelined model training across edge devices and edge servers. It employs probing-based mechanisms to tackle the new challenges raised by device-edge training. Before training begins, it probes nearby edge servers’ training performance and bootstraps model training by constructing a training pipeline with an approximate model partitioning. During the training process, EdgeMove accommodates user mobility and system dynamics by probing nearby edge servers’ training performance adaptively and adapting the training pipeline proactively. Extensive experiments are conducted with two popular DNN models trained on four datasets for three ML tasks. The results demonstrate that EdgeMove achieves a 1.3 × -2.1 × speedup over the state-of-the-art scheme.

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world’s web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed; and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×.

Federated learning (FL) has been widely acknowledged as a promising solution to training machine learning (ML) model training with privacy preservation. To reduce the traffic overheads incurred by FL systems, edge servers have been included between clients and the parameter server to aggregate clients’ local models. Recent studies on this edge-assisted hierarchical FL scheme have focused on ensuring or accelerating model convergence by coping with various factors, e.g., uncertain network conditions, unreliable clients, heterogeneous compute resources, etc. This paper presents our three new discoveries of the edge-assisted hierarchical FL scheme: 1) it wastes significant time during its two-phase training rounds; 2) it does not recognize or utilize model diversity when producing a global model; and 3) it is vulnerable to model poisoning attacks. To overcome these drawbacks, we propose FedEdge, a novel edge-assisted hierarchical FL scheme that accelerates model training with asynchronous local federated training and adaptive model aggregation. Extensive experiments are conducted on two widely-used public datasets. The results demonstrate that, compared with state-of-the-art FL schemes, FedEdge accelerates model convergence by 1.14 × −3.20 ×, and improves model accuracy by 2.14% - 6.63%.

Powered by the massive data generated by the blossom of mobile and Web-of-Things (WoT) devices, Deep Neural Networks (DNNs) have developed both in accuracy and size in recent years. Conventional cloud-based DNN training incurs rapidly-increasing data and model transmission overheads as well as privacy issues. Mobile edge computing (MEC) provides a promising solution by facilitating DNN model training on edge servers at the network edge. However, edge servers often suffer from constrained resources and need to collaborate on DNN training. Unfortunately, managed by different telecoms, edge servers cannot properly collaborate with each other without incentives and trust. In this paper, we introduce PipeEdge, a scheme that promotes collaborative edge training between edge servers by introducing incentives and trust based on blockchain. Under the PipeEdge scheme, edge servers can hire trustworthy workers for pipelined DNN training tasks based on model parallelism. We implement PipeEdge and evaluate it comprehensively with four different DNN models. The results show that it outperforms state-of-the-art schemes by up to 173.98% with negligible overheads.

Mobile edge computing (MEC) offers the infrastructure for improving data caching performance structurally by deploying edge servers at the network edge within users' close geographic proximity. Popular data like viral videos can be cached on edge servers to serve users with low latency. Investigating the integrity of these edge data is critical and challenging as edge servers often suffer from unreliability and constrained resources. Meanwhile, EDI (edge data integrity) investigation must be performed by edge servers collaboratively at the edge to avoid excessive backhaul network traffic. There are two main challenges in practice: 1) there is a lack of Byzantine-tolerant collaborative investigation method; and 2) edge servers may be reluctant to collaborate without proper incentives. To tackle these challenges systematically, this paper proposes a novel scheme named EdgeWatch to enable robust and collaborative EDI investigation in a decentralized manner based on blockchain. Under EdgeWatch, edge servers collaborate on EDI investigation following a novel integrity consensus. A blockchain system comprises of three main components is built as the infrastructure to facilitate integrity consensus: 1) an incentive mechanism that motivates edge servers to participate in EDI investigation; 2) a reputation system that elects reliable leaders for block consensus; and 3) a leader randomization technique that protects leaders from targeted attacks. We evaluate it against three representative schemes experimentally. The results demonstrate the high precision, efficiency, and robustness of EdgeWatch.

Machine learning (ML) is powering a rapidly-increasing number of web applications. As a crucial part of 5G, edge computing facilitates edge artificial intelligence (AI) by ML model training and inference at the network edge on edge servers. Compared with centralized cloud AI, edge AI enables low-latency ML inference which is critical to many delay-sensitive web applications, e.g., web AR/VR, web gaming and Web-of-Things applications. Existing studies of edge AI focused on resource and performance optimization in training and inference, leveraging edge computing merely as a tool to accelerate training and inference processes. However, the unique ability of edge computing to process data with context awareness, a powerful feature for building the web-of-things for smart cities, has not been properly explored. In this paper, we propose a novel framework named Pyramid that unleashes the potential of edge AI by facilitating homogeneous and heterogeneous hierarchical ML inferences. We motivate and present Pyramid with traffic prediction as an illustrative example, and evaluate it through extensive experiments conducted on two real-world datasets. The results demonstrate the superior performance of Pyramid neural networks in hierarchical traffic prediction and weather analysis.

Edge computing (EC) has recently emerged as a novel computing paradigm that offers users low-latency services. Suffering from constrained computing resources due to their limited physical sizes, edge servers cannot always handle all the incoming computation tasks timely when they operate independently. They often need to cooperate through peer-offloading. Deployed and managed by different stakeholders, edge servers operate in a distrusted environment. Trust and incentive are the two main issues that challenge cooperative computing between them. Another unique challenge in the EC environment is to facilitate trust and incentive in a decentralized manner. To tackle these challenges systematically, this paper proposes CoopEdge, a novel blockchain-based decentralized platform, to drive and support cooperative edge computing. On CoopEdge, an edge server can publish a computation task for other edge servers to contend for. A winner is selected from candidate edge servers based on their reputations. After that, a consensus is reached among edge servers to record the performance in task execution on blockchain. We implement CoopEdge based on Hyperledger Sawtooth and evaluate it experimentally against a baseline and two state-of-the-art implementations in a simulated EC environment. The results validate the usefulness of CoopEdge and demonstrate its performance.

Multiple multi-dimensional data streams are ubiquitous in the modern world, such as IoT applications, GIS applications and social networks. Detecting anomalies in such data streams in real-time is an important and challenging task. It is able to provide valuable information from data and then assists decision-making. However, exiting approaches for anomaly detection in multi-dimensional data streams have not properly considered the correlations among multiple multi-dimensional streams. Moreover, for multi-dimensional streaming data, online detection speed is often an important concern. In this paper, we propose a fast yet effective anomaly detection approach in multiple multi-dimensional data streams. This is based on a combination of ideas, i.e., stream pre-processing, locality sensitive hashing and dynamic isolation forest. Experiments on real datasets demonstrate that our approach achieves a magnitude increase in its efficiency compared with state-of-the-art approaches while maintaining competitive detection accuracy.