Showing papers by "Qiang Yang published in 2020"

Federated Learning in Mobile Edge Networks: A Comprehensive Survey

Abstract: In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications, e.g., for medical purposes and in vehicular networks. Traditional cloud-based Machine Learning (ML) approaches require the data to be centralized in a cloud server or data center. However, this results in critical issues related to unacceptable latency and communication inefficiency. To this end, Mobile Edge Computing (MEC) has been proposed to bring intelligence closer to the edge, where data is produced. However, conventional enabling technologies for ML at mobile edge networks still require personal data to be shared with external parties, e.g., edge servers. Recently, in light of increasingly stringent data privacy legislations and growing privacy concerns, the concept of Federated Learning (FL) has been introduced. In FL, end devices use their local data to train an ML model required by the server. The end devices then send the model updates rather than raw data to the server for aggregation. FL can serve as an enabling technology in mobile edge networks since it enables the collaborative training of an ML model and also enables DL for mobile edge network optimization. However, in a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved. This raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale. In this survey, we begin with an introduction to the background and fundamentals of FL. Then, we highlight the aforementioned challenges of FL implementation and review existing solutions. Furthermore, we present the applications of FL for mobile edge network optimization. Finally, we discuss the important challenges and future research directions in FL.

A Secure Federated Transfer Learning Framework

Abstract: Machine learning relies on the availability of vast amounts of data for training. However, in reality, data are mostly scattered across different organizations and cannot be easily integrated due to many legal and practical constraints. To address this important challenge in the field of machine learning, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical modeling under a data federation. FTL allows knowledge to be shared without compromising user privacy and enables complementary knowledge to be transferred across domains in a data federation, thereby enabling a target-domain party to build flexible and effective models by leveraging rich labels from a source domain. This framework requires minimal modifications to the existing model structure and provides the same level of accuracy as the nonprivacy-preserving transfer learning. It is flexible and can be effectively adapted to various secure multiparty machine learning tasks.

FedML: A Research Library and Benchmark for Federated Machine Learning

Abstract: Federated learning (FL) is a rapidly growing research field in machine learning. However, existing FL libraries cannot adequately support diverse algorithmic development; inconsistent dataset and model usage make fair algorithm comparison challenging. In this work, we introduce FedML, an open research library and benchmark to facilitate FL algorithm development and fair performance comparison. FedML supports three computing paradigms: on-device training for edge devices, distributed computing, and single-machine simulation. FedML also promotes diverse algorithmic research with flexible and generic API design and comprehensive reference baseline implementations (optimizer, models, and datasets). We hope FedML could provide an efficient and reproducible means for developing and evaluating FL algorithms that would benefit the FL research community. We maintain the source code, documents, and user community at this https URL.

Threats to Federated Learning: A Survey

Abstract: With the emergence of data silos and popular privacy awareness, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges. Federated learning (FL) has recently emerged as a promising solution under this new reality. Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and without the system to compromise data privacy. It is thus of paramount importance to make FL system designers to be aware of the implications of future FL algorithm design on privacy-preservation. Currently, there is no survey on this topic. In this paper, we bridge this important gap in FL literature. By providing a concise introduction to the concept of FL, and a unique taxonomy covering threat models and two major attacks on FL: 1) poisoning attacks and 2) inference attacks, this paper provides an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks, and discuss promising future research directions towards more robust privacy preservation in FL.

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Abstract: We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, non-robustness, and weak-generalization when labeled nodes are scarce. In this paper, we propose a simple yet effective framework---GRAPH RANDOM NEURAL NETWORKS (GRAND)---to address these issues. In GRAND, we first design a random propagation strategy to perform graph data augmentation. Then we leverage consistency regularization to optimize the prediction consistency of unlabeled nodes across different data augmentations. Extensive experiments on graph benchmark datasets suggest that GRAND significantly outperforms state-of-the-art GNN baselines on semi-supervised node classification. Finally, we show that GRAND mitigates the issues of over-smoothing and non-robustness, exhibiting better generalization behavior than existing GNNs. The source code of GRAND is publicly available at this https URL.

A Fairness-aware Incentive Scheme for Federated Learning

Abstract: In federated learning (FL), data owners "share" their local data in a privacy preserving manner in order to build a federated model, which in turn, can be used to generate revenues for the participants. However, in FL involving business participants, they might incur significant costs if several competitors join the same federation. Furthermore, the training and commercialization of the models will take time, resulting in delays before the federation accumulates enough budget to pay back the participants. The issues of costs and temporary mismatch between contributions and rewards have not been addressed by existing payoff-sharing schemes. In this paper, we propose the Federated Learning Incentivizer (FLI) payoff-sharing scheme. The scheme dynamically divides a given budget in a context-aware manner among data owners in a federation by jointly maximizing the collective utility while minimizing the inequality among the data owners, in terms of the payoff gained by them and the waiting time for receiving payoff. Extensive experimental comparisons with five state-of-the-art payoff-sharing schemes show that FLI is the most attractive to high quality data owners and achieves the highest expected revenue for a data federation.

Privacy and Robustness in Federated Learning: Attacks and Defenses.

Abstract: As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.

Hierarchical Incentive Mechanism Design for Federated Machine Learning in Mobile Networks

Abstract: In recent years, the enhanced sensing and computation capabilities of Internet-of-Things (IoT) devices have opened the doors to several mobile crowdsensing applications. In mobile crowdsensing, a model owner announces a sensing task following which interested workers collect the required data. However, in some cases, a model owner may have insufficient data samples to build an effective machine learning model. To this end, we propose a federated learning (FL)-based privacy-preserving approach to facilitate collaborative machine learning among multiple model owners in mobile crowdsensing. Our system model allows collaborative machine learning without compromising data privacy given that only the model parameters instead of the raw data are exchanged within the federation. However, there are two main challenges of incentive mismatches between workers and model owners, as well as among model owners. For the former, we leverage on the self-revealing mechanism in the contract theory under information asymmetry. For the latter, to ensure the stability of a federation through preventing free-riding attacks, we use the coalitional game theory approach that rewards model owners based on their marginal contributions. Considering the inherent hierarchical structure of the involved entities, we propose a hierarchical incentive mechanism framework. Using the backward induction, we first solve the contract formulation and then proceed to solve the coalitional game with the merge and split algorithm. The numerical results validate the performance efficiency of our proposed hierarchical incentive mechanism design, in terms of incentive compatibility of our contract design and fair payoffs of model owners in stable federation formation.

FedVision: An Online Visual Object Detection Platform Powered by Federated Learning

Abstract: Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (e.g., fire hazard monitoring). However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored large training datasets following the current approach. Federated learning (FL) is a promising approach to resolve this challenge. Nevertheless, there currently lacks an easy to use tool to enable computer vision application developers who are not experts in federated learning to conveniently leverage this technology and apply it in their systems. In this paper, we report FedVision - a machine learning engineering platform to support the development of federated learning powered computer vision applications. The platform has been deployed through a collaboration between WeBank and Extreme Vision to help customers develop computer vision-based safety monitoring solutions in smart city applications. Over four months of usage, it has achieved significant efficiency improvement and cost reduction while removing the need to transmit sensitive data for three major corporate customers. To the best of our knowledge, this is the first real application of FL in computer vision-based tasks.

FedVision: An Online Visual Object Detection Platform Powered by Federated Learning

Abstract: Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (eg, fire hazard monitoring) However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored large training datasets following the current approach Federated learning (FL) is a promising approach to resolve this challenge Nevertheless, there currently lacks an easy to use tool to enable computer vision application developers who are not experts in federated learning to conveniently leverage this technology and apply it in their systems In this paper, we report FedVision - a machine learning engineering platform to support the development of federated learning powered computer vision applications The platform has been deployed through a collaboration between WeBank and Extreme Vision to help customers develop computer vision-based safety monitoring solutions in smart city applications Over four months of usage, it has achieved significant efficiency improvement and cost reduction while removing the need to transmit sensitive data for three major corporate customers To the best of our knowledge, this is the first real application of FL in computer vision-based tasks

Threats to Federated Learning

Abstract: As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges. Federated learning (FL) has recently emerged as a promising solution under this new reality. Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and outside of the system to compromise data privacy. It is thus of paramount importance to make FL system designers aware of the implications of future FL algorithm design on privacy-preservation. Currently, there is no survey on this topic. In this chapter, we bridge this important gap in FL literature. By providing a concise introduction to the concept of FL, and a unique taxonomy covering threat models and two major attacks on FL: 1) poisoning attacks and 2) inference attacks, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks, and discuss promising future research directions towards more robust privacy preservation in FL.

Transfer Learning with Dynamic Distribution Adaptation

Abstract: Transfer learning aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions. However, in real applications, the marginal and conditional distributions usually have different contributions to the domain discrepancy. Existing methods fail to quantitatively evaluate the different importance of these two distributions, which will result in unsatisfactory transfer performance. In this article, we propose a novel concept called Dynamic Distribution Adaptation (DDA), which is capable of quantitatively evaluating the relative importance of each distribution. DDA can be easily incorporated into the framework of structural risk minimization to solve transfer learning problems. On the basis of DDA, we propose two novel learning algorithms: (1) Manifold Dynamic Distribution Adaptation (MDDA) for traditional transfer learning, and (2) Dynamic Distribution Adaptation Network (DDAN) for deep transfer learning. Extensive experiments demonstrate that MDDA and DDAN significantly improve the transfer learning performance and set up a strong baseline over the latest deep and adversarial methods on digits recognition, sentiment analysis, and image classification. More importantly, it is shown that marginal and conditional distributions have different contributions to the domain divergence, and our DDA is able to provide good quantitative evaluation of their relative importance, which leads to better performance. We believe this observation can be helpful for future research in transfer learning.

A Sustainable Incentive Scheme for Federated Learning

Abstract: In federated learning (FL), a federation distributedly trains a collective machine learning model by leveraging privacy preserving technologies. However, FL participants need to incur some cost for contributing to the FL models. The training and commercialization of the models will take time. Thus, there will be delays before the federation could pay back the participants. This temporary mismatch between contributions and rewards has not been accounted for by existing payoff-sharing schemes. To address this limitation, we propose the FL incentivizer (FLI). It dynamically divides a given budget in a context-aware manner among data owners in a federation by jointly maximizing the collective utility while minimizing the inequality among the data owners, in terms of the payoff received and the waiting time for receiving payoffs. Comparisons with five state-of-the-art payoff-sharing schemes show that FLI attracts high-quality data owners and achieves the highest expected revenue for a federation.

A Distributed Swarm Optimizer With Adaptive Communication for Large-Scale Optimization

Abstract: Large-scale optimization with high dimensionality and high computational cost becomes ubiquitous nowadays. To tackle such challenging problems efficiently, devising distributed evolutionary computation algorithms is imperative. To this end, this paper proposes a distributed swarm optimizer based on a special master–slave model. Specifically, in this distributed optimizer, the master is mainly responsible for communication with slaves, while each slave iterates a swarm to traverse the solution space. An asynchronous and adaptive communication strategy based on the request–response mechanism is especially devised to let the slaves communicate with the master efficiently. Particularly, the communication between the master and each slave is adaptively triggered during the iteration. To aid the slaves to search the space efficiently, an elite-guided learning strategy is especially designed via utilizing elite particles in the current swarm and historically best solutions found by different slaves to guide the update of particles. Together, this distributed optimizer asynchronously iterates multiple swarms to collaboratively seek the optimum in parallel. Extensive experiments on a widely used large-scale benchmark set substantiate that the distributed optimizer could: 1) achieve competitive effectiveness in terms of solution quality as compared to the state-of-the-art large-scale methods; 2) accelerate the execution of the algorithm in comparison with the sequential one and obtain almost linear speedup as the number of cores increases; and 3) preserve a good scalability to solve higher dimensional problems.

Ant Colony Optimization for the Control of Pollutant Spreading on Social Networks

Abstract: The rapid development of online social networks not only enables prompt and convenient dissemination of desirable information but also incurs fast and wide propagation of undesirable information. A common way to control the spread of pollutants is to block some nodes, but such a strategy may affect the service quality of a social network and leads to a high control cost if too many nodes are blocked. This paper considers the node selection problem as a biobjective optimization problem to find a subset of nodes to be blocked so that the effect of the control is maximized while the cost of the control is minimized. To solve this problem, we design an ant colony optimization algorithm with an adaptive dimension size selection under the multiobjective evolutionary algorithm framework based on decomposition (MOEA/D-ADACO). The proposed algorithm divides the biobjective problem into a set of single-objective subproblems and each ant takes charge of optimizing one subproblem. Moreover, two types of pheromone and heuristic information are incorporated into MOEA/D-ADACO, that is, pheromone and heuristic information of dimension size selection and that of node selection. While constructing solutions, the ants first determine the dimension size according to the former type of pheromone and heuristic information. Then, the ants select a specific number of nodes to build solutions according to the latter type of pheromone and heuristic information. Experiments conducted on a set of real-world online social networks confirm that the proposed biobjective optimization model and the developed MOEA/D-ADACO are promising for the pollutant spreading control.

Active Distribution System Reinforcement Planning With EV Charging Stations—Part I: Uncertainty Modeling and Problem Formulation

Abstract: Due to the associated uncertainties, the large-scale deployment of electric vehicles (EVs) and renewable distributed generation is a major challenge faced by the modern distribution systems. The first part of this two-paper series proposes a scenario-based stochastic model for the multistage joint reinforcement planning of the distribution systems and the electric vehicle charging stations (EVCSs). The historical EV charging demand is first determined using the Markovian analysis of EV driving patterns and charging demand. A scenario matrix, based on the heuristic moment matching method, is then generated to characterize the stochastic features and correlation among historical wind and photovoltaic generation, and conventional loads and EV demands. The scenario matrix is then utilized to formulate the expansion planning framework, aiming at the minimization of the investment and operational costs. The proposed expansion plan determines the optimal construction/reinforcement of substations, EVCSs, and feeders, in addition to the placement of wind and photovoltaic generators, and capacitor banks over the multi-stage planning horizon. In the second companion paper, the effectiveness and scalability of the proposed model is assessed through case studies in the 18-bus and the IEEE 123-bus distribution systems, respectively.

An Unmanned Inspection System for Multiple Defects Detection in Photovoltaic Plants

Abstract: Condition monitoring and fault diagnosis of photovoltaic modules are essential to ensure the efficient and reliable operation of large-scale photovoltaic plants. This article presents an algorithmic solution for the rapid and sensitive detection of photovoltaic modules with multiple visible defects by an image analyzing apparatus mounted onto an unmanned aerial vehicle. The proposed solution is composed of three stages to efficiently and accurately analyze various forms of module defects. First, the Kirsch operator is employed to identify the anomalous regions, which can significantly reduce the computational complexity, and error rate. Afterward, a deep convolutional neural network is adopted to extract defect features. Finally, a multiple classification support vector machine is developed to facilitate the defects detection decision-making. The proposed solution is extensively evaluated by the comprehensive dataset collected from real-world solar photovoltaic plants. The experimental results clearly demonstrate the effectiveness of our solution for photovoltaic modules diagnosis with multiple visible defects.

Data-Driven Solution for Optimal Pumping Units Scheduling of Smart Water Conservancy

Abstract: Internet of Things (IoT) technology provides the necessary foundation and support for smart city water management. To address the challenge of river pollution prevention and flood control requirements in the urban river system, this article proposes a data-driven model to carry out the optimal operation scheduling of water diversion and drainage pumping stations in the presence of the complex hydrometeorological constraints. The proposed solution in the model predictive control (MPC) framework first adopts the long short-term memory (LSTM) network through supervised learning from IoT data to simulate and predict the river flow dynamics and the water quality. Consequently, the optimal scheduling of controllable pumping stations to minimize the operational cost (e.g., the flocculant consumption) can be formulated as a stochastic optimization problem, while meeting the river flood control and water quality constraints. The particle swarm optimization (PSO) algorithm is further used to solve the above unit commitment (UC) optimization problem and obtain the optimal operational schedules of the water pumping units (e.g., startup time and working periods). The performance of the proposed optimal water pumping scheduling solution is evaluated through a field case study of the urban river diversion system and the numerical results clearly confirm its effectiveness and improved economic performance compared to the existing benchmark solution.

Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective

Abstract: Federated Learning (FL) proposed in recent years has received significant attention from researchers in that it can bring separate data sources together and build machine learning models in a collaborative but private manner. Yet, in most applications of FL, such as keyboard prediction, labeling data requires virtually no additional efforts, which is not generally the case. In reality, acquiring large-scale labeled datasets can be extremely costly, which motivates research works that exploit unlabeled data to help build machine learning models. However, to the best of our knowledge, few existing works aim to utilize unlabeled data to enhance federated learning, which leaves a potentially promising research topic. In this paper, we identify the need to exploit unlabeled data in FL, and survey possible research fields that can contribute to the goal.

A Federated Recommender System for Online Services

Abstract: Due to privacy and security constraints, directly sharing user data between parties is undesired. Such decentralized data silo issues commonly exist in recommender systems. In general, recommender systems are data-driven. The more data it uses, the better performance it obtains. The data silo issues is a severe limitation of the recommender’s performance. Federated learning is an emerging technology, which bridges the data silos and builds machine learning models without compromising user privacy and data security. We design a recommender system based on federated learning. It is known as the federated recommender system. The system implements plenty of popular algorithms to support various online recommendation services. The algorithm implementation is open-sourced. We also deploy the system on a real-world content recommendation application, achieving significant performance improvement. In this demonstration, we present the architecture of the federated recommender system and give an online demo to show its detailed working procedures and results in content recommendations.

Bioinspired Patterned Bubbles for Broad and Low-Frequency Acoustic Blocking

Abstract: Bubble crystals in water are expected to achieve the broad and low-frequency acoustic band gaps that are crucial for acoustic blocking. However, preparing patterned bubble crystals in water remains a challenge because of the instability of bubbly liquids. Here, inspired by biological superhydrophobic systems, we report a simple and rapid approach to prepare patterned bubble arrays in water and their applications in low-frequency acoustic blocking. Patterned bubbles with the desired size, shape, and position can be prepared. Single-layer bubble arrays can block the sounds at low frequencies because of local resonance. By varying the size and distance of the bubbles without changing the thickness, the operating frequency can change from 9 to 1756 kHz. Besides, by preparing multilayer bubbles, broad and low-frequency acoustic band gaps can be achieved, with the generalized width of γ (ratio of the bandgap width to its start frequency) reaching 1.26. This method provides a feasible strategy to control acoustic waves at low frequencies for applications such as acoustic blocking, focusing, imaging, and detecting.

Improving and Stabilizing Perovskite Solar Cells with Incorporation of Graphene in the Spiro-OMeTAD Layer: Suppressed Li Ions Migration and Improved Charge Extraction

Abstract: Perovskite solar cells (PSCs) have achieved a huge success in power conversion efficiency (PCE), although they still suffer from the long-term stability problem caused by the intrinsic sensitivity ...

Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks

Abstract: This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks First, we propose to quantitatively measure the trade-off between model accuracy and privacy losses incurred by reconstruction, tracing and membership attacks Second, we formulate reconstruction attacks as solving a noisy system of linear equations, and prove that attacks are guaranteed to be defeated if condition (2) is unfulfilled Third, based on theoretical analysis, a novel Secret Polarization Network (SPN) is proposed to thwart privacy attacks, which pose serious challenges to existing PPDL methods Extensive experiments showed that model accuracies are improved on average by 5-20% compared with baseline mechanisms, in regimes where data privacy are satisfactorily protected

Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages

Abstract: Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks. However, mPLM-based methods usually involve two problems: (1) simply fine-tuning may not adapt general-purpose multilingual representations to be task-aware on low-resource languages; (2) ignore how cross-lingual adaptation happens for downstream tasks. To address the issues, we propose a meta graph learning (MGL) method. Unlike prior works that transfer from scratch, MGL can learn to cross-lingual transfer by extracting meta-knowledge from historical CLT experiences (tasks), making mPLM insensitive to low-resource languages. Besides, for each CLT task, MGL formulates its transfer process as information propagation over a dynamic graph, where the geometric structure can automatically capture intrinsic language relationships to explicitly guide cross-lingual transfer. Empirically, extensive experiments on both public and real-world datasets demonstrate the effectiveness of the MGL method.