arXiv subjects

Shiqiang Wang

Publications and source records attributed to Shiqiang Wang.

At least 91 records · Page 5Linked to original sources

arXiv2020

Sharing Models or Coresets: A Study based on Membership Inference Attack

Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different approaches have been proposed: collecting and aggregating local models (federated learning) and collecting and training over representative data summaries (coreset). While each approach preserves data privacy to some extent thanks to not sharing the raw data, the exact extent of protection is unclear under sophisticated attacks that try to infer the raw data from the shared information. We present the first comparison between the two approaches in terms of target model accuracy, communication cost, and data privacy, where the last is measured by the accuracy of a state-of-the-art attack strategy called the membership inference attack. Our experiments quantify the accuracy-privacy-cost tradeoff of each approach, and reveal a nontrivial comparison that can be used to guide the design of model training processes.

cs.LG↗

arXiv2020

Overcoming Noisy and Irrelevant Data in Federated Learning

Many image and vision applications require a large amount of data for model training. Collecting all such data at a central location can be challenging due to data privacy and communication bandwidth restrictions. Federated learning is an effective way of training a machine learning model in a distributed manner from local data collected by client devices, which does not require exchanging the raw data among clients. A challenge is that among the large variety of data collected at each client, it is likely that only a subset is relevant for a learning task while the rest of data has a negative impact on model training. Therefore, before starting the learning process, it is important to select the subset of data that is relevant to the given federated learning task. In this paper, we propose a method for distributedly selecting relevant data, where we use a benchmark model trained on a small benchmark dataset that is task-specific, to evaluate the relevance of individual data samples at each client and select the data with sufficiently high relevance. Then, each client only uses the selected subset of its data in the federated learning process. The effectiveness of our proposed approach is evaluated on multiple real-world image datasets in a simulated system with a large number of clients, showing up to $25\%$ improvement in model accuracy compared to training with all data.

cs.LG↗

arXiv2020

Robust Coreset Construction for Distributed Machine Learning

Coreset, which is a summary of the original dataset in the form of a small weighted set in the same sample space, provides a promising approach to enable machine learning over distributed data. Although viewed as a proxy of the original dataset, each coreset is only designed to approximate the cost function of a specific machine learning problem, and thus different coresets are often required to solve different machine learning problems, increasing the communication overhead. We resolve this dilemma by developing robust coreset construction algorithms that can support a variety of machine learning problems. Motivated by empirical evidence that suitably-weighted k-clustering centers provide a robust coreset, we harden the observation by establishing theoretical conditions under which the coreset provides a guaranteed approximation for a broad range of machine learning problems, and developing both centralized and distributed algorithms to generate coresets satisfying the conditions. The robustness of the proposed algorithms is verified through extensive experiments on diverse datasets with respect to both supervised and unsupervised learning problems.

cs.LG↗

arXiv2020

Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach

Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication overhead and improve the overall efficiency of FL, gradient sparsification (GS) can be applied, where instead of the full gradient, only a small subset of important elements of the gradient is communicated. Existing work on GS uses a fixed degree of gradient sparsity for i.i.d.-distributed data within a datacenter. In this paper, we consider adaptive degree of sparsity and non-i.i.d. local datasets. We first present a fairness-aware GS method which ensures that different clients provide a similar amount of updates. Then, with the goal of minimizing the overall training time, we propose a novel online learning formulation and algorithm for automatically determining the near-optimal communication and computation trade-off that is controlled by the degree of gradient sparsity. The online learning algorithm uses an estimated sign of the derivative of the objective function, which gives a regret bound that is asymptotically equal to the case where exact derivative is available. Experiments with real datasets confirm the benefits of our proposed approaches, showing up to $40\%$ improvement in model accuracy for a finite training time.

cs.LG↗

arXiv2020

Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art

Nowadays, devices are equipped with advanced sensors with higher processing/computing capabilities. Further, widespread Internet availability enables communication among sensing devices. As a result, vast amounts of data are generated on edge devices to drive Internet-of-Things (IoT), crowdsourcing, and other emerging technologies. The collected extensive data can be pre-processed, scaled, classified, and finally, used for predicting future events using machine learning (ML) methods. In traditional ML approaches, data is sent to and processed in a central server, which encounters communication overhead, processing delay, privacy leakage, and security issues. To overcome these challenges, each client can be trained locally based on its available data and by learning from the global model. This decentralized learning structure is referred to as Federated Learning (FL). However, in large-scale networks, there may be clients with varying computational resource capabilities. This may lead to implementation and scalability challenges for FL techniques. In this paper, we first introduce some recently implemented real-life applications of FL. We then emphasize on the core challenges of implementing the FL algorithms from the perspective of resource limitations (e.g., memory, bandwidth, and energy budget) of client clients. We finally discuss open issues associated with FL and highlight future directions in the FL area concerning resource-constrained devices.

cs.LG↗

arXiv2019

Distilling On-Device Intelligence at the Network Edge

Devices at the edge of wireless networks are the last mile data sources for machine learning (ML). As opposed to traditional ready-made public datasets, these user-generated private datasets reflect the freshest local environments in real time. They are thus indispensable for enabling mission-critical intelligent systems, ranging from fog radio access networks (RANs) to driverless cars and e-Health wearables. This article focuses on how to distill high-quality on-device ML models using fog computing, from such user-generated private data dispersed across wirelessly connected devices. To this end, we introduce communication-efficient and privacy-preserving distributed ML frameworks, termed fog ML (FML), wherein on-device ML models are trained by exchanging model parameters, model outputs, and surrogate data. We then present advanced FML frameworks addressing wireless RAN characteristics, limited on-device resources, and imbalanced data distributions. Our study suggests that the full potential of FML can be reached by co-designing communication and distributed ML operations while accounting for heterogeneous hardware specifications, data characteristics, and user requirements.

cs.IT↗

arXiv2019

MaxHedge: Maximising a Maximum Online

We introduce a new online learning framework where, at each trial, the learner is required to select a subset of actions from a given known action set. Each action is associated with an energy value, a reward and a cost. The sum of the energies of the actions selected cannot exceed a given energy budget. The goal is to maximise the cumulative profit, where the profit obtained on a single trial is defined as the difference between the maximum reward among the selected actions and the sum of their costs. Action energy values and the budget are known and fixed. All rewards and costs associated with each action change over time and are revealed at each trial only after the learner's selection of actions. Our framework encompasses several online learning problems where the environment changes over time; and the solution trades-off between minimising the costs and maximising the maximum reward of the selected subset of actions, while being constrained to an action energy budget. The algorithm that we propose is efficient and general in that it may be specialised to multiple natural online combinatorial problems.

cs.LG↗

arXiv2019

Service Placement with Provable Guarantees in Heterogeneous Edge Computing Systems

Mobile edge computing (MEC) is a promising technique for providing low-latency access to services at the network edge. The services are hosted at various types of edge nodes with both computation and communication capabilities. Due to the heterogeneity of edge node characteristics and user locations, the performance of MEC varies depending on where the service is hosted. In this paper, we consider such a heterogeneous MEC system, and focus on the problem of placing multiple services in the system to maximize the total reward. We show that the problem is NP-hard via reduction from the set cover problem, and propose a deterministic approximation algorithm to solve the problem, which has an approximation ratio that is not worse than $\left(1-e^{-1}\right)/4$. The proposed algorithm is based on two sub-routines that are suitable for small and arbitrarily sized services, respectively. The algorithm is designed using a novel way of partitioning each edge node into multiple slots, where each slot contains one service. The approximation guarantee is obtained via a specialization of the method of conditional expectations, which uses a randomized procedure as an intermediate step. In addition to theoretical guarantees, simulation results also show that the proposed algorithm outperforms other state-of-the-art approaches.

cs.DC↗

arXiv2019

Online Collection and Forecasting of Resource Utilization in Large-Scale Distributed Systems

Large-scale distributed computing systems often contain thousands of distributed nodes (machines). Monitoring the conditions of these nodes is important for system management purposes, which, however, can be extremely resource demanding as this requires collecting local measurements of each individual node and constantly sending those measurements to a central controller. Meanwhile, it is often useful to forecast the future system conditions for various purposes such as resource planning/allocation and anomaly detection, but it is usually too resource-consuming to have one forecasting model running for each node, which may also neglect correlations in observed metrics across different nodes. In this paper, we propose a mechanism for collecting and forecasting the resource utilization of machines in a distributed computing system in a scalable manner. We present an algorithm that allows each local node to decide when to transmit its most recent measurement to the central node, so that the transmission frequency is kept below a given constraint value. Based on the measurements received from local nodes, the central node summarizes the received data into a small number of clusters. Since the cluster partitioning can change over time, we also present a method to capture the evolution of clusters and their centroids. As an effective way to reduce the amount of computation, time-series forecasting models are trained on the time-varying centroids of each cluster, to forecast the future resource utilizations of a group of local nodes. The effectiveness of our proposed approach is confirmed by extensive experiments using multiple real-world datasets.

cs.DC↗

arXiv2019

Dynamic Service Migration in Mobile Edge Computing Based on Markov Decision Process

In mobile edge computing, local edge servers can host cloud-based services, which reduces network overhead and latency but requires service migrations as users move to new locations. It is challenging to make migration decisions optimally because of the uncertainty in such a dynamic cloud environment. In this paper, we formulate the service migration problem as a Markov Decision Process (MDP). Our formulation captures general cost models and provides a mathematical framework to design optimal service migration policies. In order to overcome the complexity associated with computing the optimal policy, we approximate the underlying state space by the distance between the user and service locations. We show that the resulting MDP is exact for uniform one-dimensional user mobility while it provides a close approximation for uniform two-dimensional mobility with a constant additive error. We also propose a new algorithm and a numerical technique for computing the optimal solution which is significantly faster than traditional methods based on standard value or policy iteration. We illustrate the application of our solution in practical scenarios where many theoretical assumptions are relaxed. Our evaluations based on real-world mobility traces of San Francisco taxis show superior performance of the proposed solution compared to baseline solutions.

cs.DC↗

arXiv2019

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. In this paper, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of machine learning models that are trained using gradient-descent based approaches. We analyze the convergence bound of distributed gradient descent from a theoretical point of view, based on which we propose a control algorithm that determines the best trade-off between local update and global parameter aggregation to minimize the loss function under a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real datasets, both on a networked prototype system and in a larger-scale simulated environment. The experimentation results show that our proposed approach performs near to the optimum with various machine learning models and different data distributions.

cs.DC↗

arXiv2017

Location Privacy in Mobile Edge Clouds: A Chaff-based Approach

In this paper, we consider user location privacy in mobile edge clouds (MECs). MECs are small clouds deployed at the network edge to offer cloud services close to mobile users, and many solutions have been proposed to maximize service locality by migrating services to follow their users. Co-location of a user and his service, however, implies that a cyber eavesdropper observing service migrations between MECs can localize the user up to one MEC coverage area, which can be fairly small (e.g., a femtocell). We consider using chaff services to defend against such an eavesdropper, with focus on strategies to control the chaffs. Assuming the eavesdropper performs maximum likelihood (ML) detection, we consider both heuristic strategies that mimic the user's mobility and optimized strategies designed to minimize the detection or tracking accuracy. We show that a single chaff controlled by the optimal strategy or its online variation can drive the eavesdropper's tracking accuracy to zero when the user's mobility is sufficiently random. We further propose extended strategies that utilize randomization to defend against an advanced eavesdropper aware of the strategy. The efficacy of our solutions is verified through both synthetic and trace-driven simulations.

cs.DC↗

arXiv2017

Live Service Migration in Mobile Edge Clouds

Mobile edge clouds (MECs) bring the benefits of the cloud closer to the user, by installing small cloud infrastructures at the network edge. This enables a new breed of real-time applications, such as instantaneous object recognition and safety assistance in intelligent transportation systems, that require very low latency. One key issue that comes with proximity is how to ensure that users always receive good performance as they move across different locations. Migrating services between MECs is seen as the means to achieve this. This article presents a layered framework for migrating active service applications that are encapsulated either in virtual machines (VMs) or containers. This layering approach allows a substantial reduction in service downtime. The framework is easy to implement using readily available technologies, and one of its key advantages is that it supports containers, which is a promising emerging technology that offers tangible benefits over VMs. The migration performance of various real applications is evaluated by experiments under the presented framework. Insights drawn from the experimentation results are discussed.

cs.DC↗

arXiv2017

Online Placement of Multi-Component Applications in Edge Computing Environments

Mobile edge computing is a new cloud computing paradigm which makes use of small-sized edge-clouds to provide real-time services to users. These mobile edge-clouds (MECs) are located in close proximity to users, thus enabling users to seamlessly access applications running on MECs. Due to the co-existence of the core (centralized) cloud, users, and one or multiple layers of MECs, an important problem is to decide where (on which computational entity) to place different components of an application. This problem, known as the application or workload placement problem, is notoriously hard, and therefore, heuristic algorithms without performance guarantees are generally employed in common practice, which may unknowingly suffer from poor performance as compared to the optimal solution. In this paper, we address the application placement problem and focus on developing algorithms with provable performance bounds. We model the user application as an application graph and the physical computing system as a physical graph, with resource demands/availabilities annotated on these graphs. We first consider the placement of a linear application graph and propose an algorithm for finding its optimal solution. Using this result, we then generalize the formulation and obtain online approximation algorithms with polynomial-logarithmic (poly-log) competitive ratio for tree application graph placement. We jointly consider node and link assignment, and incorporate multiple types of computational resources at nodes.

cs.DC↗

arXiv2016

Dynamic Service Placement for Mobile Micro-Clouds with Predicted Future Costs

Mobile micro-clouds are promising for enabling performance-critical cloud applications. However, one challenge therein is the dynamics at the network edge. In this paper, we study how to place service instances to cope with these dynamics, where multiple users and service instances coexist in the system. Our goal is to find the optimal placement (configuration) of instances to minimize the average cost over time, leveraging the ability of predicting future cost parameters with known accuracy. We first propose an offline algorithm that solves for the optimal configuration in a specific look-ahead time-window. Then, we propose an online approximation algorithm with polynomial time-complexity to find the placement in real-time whenever an instance arrives. We analytically show that the online algorithm is $O(1)$-competitive for a broad family of cost functions. Afterwards, the impact of prediction errors is considered and a method for finding the optimal look-ahead window size is proposed, which minimizes an upper bound of the average actual cost. The effectiveness of the proposed approach is evaluated by simulations with both synthetic and real-world (San Francisco taxi) user-mobility traces. The theoretical methodology used in this paper can potentially be applied to a larger class of dynamic resource allocation problems.

cs.DC↗

arXiv2016

End-to-End Known-Interference Cancellation (E2E-KIC) with Multi-Hop Interference

Recently, end-to-end known-interference cancellation (E2E-KIC) has been proposed as a promising technique for wireless networks. It sequentially cancels out the known interferences at each node so that wireless multi-hop transmission can achieve a similar throughput as single-hop transmission. Existing work on E2E-KIC assumed that the interference of a transmitter to those nodes outside the transmitter's communication range is negligible. In practice, however, this assumption is not always valid. There are many cases where a transmitter causes notable interference to nodes beyond its communication distance. From a wireless networking perspective, such interference is caused by a node to other nodes that are multiple hops away, thus we call it multi-hop interference. The presence of multi-hop interference poses fundamental challenges to E2E-KIC, where known procedures cannot be directly applied. In this paper, we propose an E2E-KIC approach which allows the existence of multi-hop interference. In particular, we present a method that iteratively cancels unknown interferences transmitted across multiple hops. We analyze mathematically why and when this approach works and the performance of it. The analysis is further supported by numerical results.

cs.IT↗

arXiv2015

Approaching Single-Hop Performance in Multi-Hop Networks: End-To-End Known-Interference Cancellation (E2E-KIC)

To improve the efficiency of wireless data communications, new physical-layer transmission methods based on known-interference cancellation (KIC) have been developed. These methods share the common idea that the interference can be cancelled when the content of it is known. Existing work on KIC mainly focuses on single-hop or two-hop networks, with physical-layer network coding (PNC) and full-duplex (FD) communications as typical examples. This paper extends the idea of KIC to general multi-hop networks, and proposes an end-to-end KIC (E2E-KIC) transmission method together with its MAC design. With E2E-KIC, multiple nodes in a flow passing through a few nodes in an arbitrary topology can simultaneously transmit and receive on the same channel. We first present a theoretical analysis on the effectiveness of E2E-KIC in an idealized case. Then, to support E2E-KIC in multi-hop networks with arbitrary topology, we propose an E2E-KIC-supported MAC protocol (E2E-KIC MAC), which is based on an extension of the Request-to-Send/Clear-to-Send (RTS/CTS) mechanism in the IEEE 802.11 MAC. We also analytically analyze the performance of the proposed E2E-KIC MAC in the presence of hidden terminals. Simulation results illustrate that the proposed E2E-KIC MAC protocol can improve the network throughput and reduce the end-to-end delay.

cs.NI↗

arXiv2015

Mobility-Induced Service Migration in Mobile Micro-Clouds

Mobile micro-cloud is an emerging technology in distributed computing, which is aimed at providing seamless computing/data access to the edge of the network when a centralized service may suffer from poor connectivity and long latency. Different from the traditional cloud, a mobile micro-cloud is smaller and deployed closer to users, typically attached to a cellular basestation or wireless network access point. Due to the relatively small coverage area of each basestation or access point, when a user moves across areas covered by different basestations or access points which are attached to different micro-clouds, issues of service performance and service migration become important. In this paper, we consider such migration issues. We model the general problem as a Markov decision process (MDP), and show that, in the special case where the mobile user follows a one-dimensional asymmetric random walk mobility model, the optimal policy for service migration is a threshold policy. We obtain the analytical solution for the cost resulting from arbitrary thresholds, and then propose an algorithm for finding the optimal thresholds. The proposed algorithm is more efficient than standard mechanisms for solving MDPs.

cs.DC↗