arXiv subjects

Ming Ding

Publications and source records attributed to Ming Ding.

At least 163 records · Page 9Linked to original sources

arXiv2021

User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization

Federated learning (FL), as a type of collaborative machine learning framework, is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. Nevertheless, from a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. To address this problem, we first make use of the concept of local differential privacy (LDP), and propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers. According to our analysis, the UDP framework can realize $(ε_{i}, δ_{i})$-LDP for the $i$-th MT with adjustable privacy protection levels by varying the variances of the artificial noise processes. We then derive a theoretical convergence upper-bound for the UDP algorithm. It reveals that there exists an optimal number of communication rounds to achieve the best learning performance. More importantly, we propose a communication rounds discounting (CRD) method. Compared with the heuristic search method, the proposed CRD method can achieve a much better trade-off between the computational complexity of searching and the convergence performance. Extensive experiments indicate that our UDP algorithm using the proposed CRD method can effectively improve both the training efficiency and model quality for the given privacy protection levels.

cs.LG↗

arXiv2021

Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization

Federated learning (FL), as a type of distributed machine learning frameworks, is vulnerable to external attacks on FL models during parameters transmissions. An attacker in FL may control a number of participant clients, and purposely craft the uploaded model parameters to manipulate system outputs, namely, model poisoning (MP). In this paper, we aim to propose effective MP algorithms to combat state-of-the-art defensive aggregation mechanisms (e.g., Krum and Trimmed mean) implemented at the server without being noticed, i.e., covert MP (CMP). Specifically, we first formulate the MP as an optimization problem by minimizing the Euclidean distance between the manipulated model and designated one, constrained by a defensive aggregation rule. Then, we develop CMP algorithms against different defensive mechanisms based on the solutions of their corresponding optimization problems. Furthermore, to reduce the optimization complexity, we propose low complexity CMP algorithms with a slight performance degradation. In the case that the attacker does not know the defensive aggregation mechanism, we design a blind CMP algorithm, in which the manipulated model will be adjusted properly according to the aggregated model generated by the unknown defensive aggregation. Our experimental results demonstrate that the proposed CMP algorithms are effective and substantially outperform existing attack mechanisms.

cs.LG↗

arXiv2021

F-manifold color algebras

In this paper, we introduce the notion of F-manifold color algebras and study their properties which extend some results for F-manifold algebras.

math.RA↗

arXiv2020

Task Offloading for Large-Scale Asynchronous Mobile Edge Computing: An Index Policy Approach

Mobile-edge computing (MEC) offloads computational tasks from wireless devices to network edge, and enables real-time information transmission and computing. Most existing work concerns a small-scale synchronous MEC system. In this paper, we focus on a large-scale asynchronous MEC system with random task arrivals, distinct workloads, and diverse deadlines. We formulate the offloading policy design as a restless multi-armed bandit (RMAB) to maximize the total discounted reward over the time horizon. However, the formulated RMAB is related to a PSPACE-hard sequential decision-making problem, which is intractable. To address this issue, by exploiting the Whittle index (WI) theory, we rigorously establish the WI indexability and derive a scalable closed-form solution. Consequently, in our WI policy, each user only needs to calculate its WI and report it to the BS, and the users with the highest indices are selected for task offloading. Furthermore, when the task completion ratio becomes the focus, the shorter slack time less remaining workload (STLW) priority rule is introduced into the WI policy for performance improvement. When the knowledge of user offloading energy consumption is not available prior to the offloading, we develop Bayesian learning-enabled WI policies, including maximum likelihood estimation, Bayesian learning with conjugate prior, and prior-swapping techniques. Simulation results show that the proposed policies significantly outperform the other existing policies.

cs.IT↗

arXiv2020

Toward an Affective Touch Robot: Subjective and Physiological Evaluation of Gentle Stroke Motion Using a Human-Imitation Hand

Affective touch offers positive psychological and physiological benefits such as the mitigation of stress and pain. If a robot could realize human-like affective touch, it would open up new application areas, including supporting care work. In this research, we focused on the gentle stroking motion of a robot to evoke the same emotions that human touch would evoke: in other words, an affective touch robot. We propose a robot that is able to gently stroke the back of a human using our designed human-imitation hand. To evaluate the emotional effects of this affective touch, we compared the results of a combination of two agents (the human-imitation hand and the human hand), at two stroke speeds (3 and 30 cm/s). The results of the subjective and physiological evaluations highlighted the following three findings: 1) the subjects evaluated strokes similarly with regard to the stroke speed of the human and human-imitation hand, in both the subjective and physiological evaluations; 2) the subjects felt greater pleasure and arousal at the faster stroke rate (30 cm/s rather than 3 cm/s); and 3) poorer fitting of the human-imitation hand due to the bending of the back had a negative emotional effect on the subjects.

cs.RO↗

arXiv2020

Blockchain Assisted Decentralized Federated Learning (BLADE-FL) with Lazy Clients

Federated learning (FL), as a distributed machine learning approach, has drawn a great amount of attention in recent years. FL shows an inherent advantage in privacy preservation, since users' raw data are processed locally. However, it relies on a centralized server to perform model aggregation. Therefore, FL is vulnerable to server malfunctions and external attacks. In this paper, we propose a novel framework by integrating blockchain into FL, namely, blockchain assisted decentralized federated learning (BLADE-FL), to enhance the security of FL. The proposed BLADE-FL has a good performance in terms of privacy preservation, tamper resistance, and effective cooperation of learning. However, it gives rise to a new problem of training deficiency, caused by lazy clients who plagiarize others' trained models and add artificial noises to conceal their cheating behaviors. To be specific, we first develop a convergence bound of the loss function with the presence of lazy clients and prove that it is convex with respect to the total number of generated blocks $K$. Then, we solve the convex problem by optimizing $K$ to minimize the loss function. Furthermore, we discover the relationship between the optimal $K$, the number of lazy clients, and the power of artificial noises used by lazy clients. We conduct extensive experiments to evaluate the performance of the proposed framework using the MNIST and Fashion-MNIST datasets. Our analytical results are shown to be consistent with the experimental results. In addition, the derived optimal $K$ achieves the minimum value of loss function, and in turn the optimal accuracy performance.

cs.LG↗

arXiv2020

When Machine Learning Meets Privacy: A Survey and Outlook

The newly emerged machine learning (e.g. deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems. Meanwhile, privacy has emerged as a big concern in this machine learning-based artificial intelligence era. It is important to note that the problem of privacy preservation in the context of machine learning is quite different from that in traditional data privacy protection, as machine learning can act as both friend and foe. Currently, the work on the preservation of privacy and machine learning (ML) is still in an infancy stage, as most existing solutions only focus on privacy problems during the machine learning process. Therefore, a comprehensive study on the privacy preservation problems and machine learning is required. This paper surveys the state of the art in privacy issues and solutions for machine learning. The survey covers three categories of interactions between privacy and machine learning: (i) private machine learning, (ii) machine learning aided privacy protection, and (iii) machine learning-based privacy attack and corresponding protection schemes. The current research progress in each category is reviewed and the key challenges are identified. Finally, based on our in-depth analysis of the area of privacy and machine learning, we point out future research directions in this field.

cs.LG↗

arXiv2020

Atomic basis of quantum cluster algebra of type $\widetilde{A}_{2n-1,1}$

Let $Q$ be the affine quiver of type $\widetilde{A}_{2n-1,1}$ and $\mathcal{A}_{q}(Q)$ be the quantum cluster algebra associated to the valued quiver $(Q,(2,2,\dots,2))$. We prove some cluster multiplication formulas, and deduce that the cluster variables associated with vertices of $Q$ satisfy a quantum analogue of the constant coefficient linear relations. We then construct two bar-invariant $\mathbb{Z}[q^{\pm\frac{1}{2}}]$-bases $\mathcal{B}$ and $\mathcal{S}$ of $\mathcal{A}_{q}(Q)$ consisting of positive elements, and prove that $\mathcal{B}$ is an atomic basis.

math.RT↗

arXiv2020

On the Generalized Cluster Algebras of Geometric Type

We develop and prove the analogs of some results shown in [Berenstein A., Fomin S., Zelevinsky A., Duke Math. J. 126 (2005), 1-52] concerning lower and upper bounds of cluster algebras to the generalized cluster algebras of geometric type. We show that lower bounds coincide with upper bounds under the conditions of acyclicity and coprimality. Consequently, we obtain the standard monomial bases of these generalized cluster algebras. Moreover, in the appendix, we prove that an acyclic generalized cluster algebra is equal to the corresponding generalized upper cluster algebra without the assumption of the existence of coprimality.

math.RA↗

arXiv2020

Integration of Blockchain and Cloud of Things: Architecture, Applications and Challenges

The blockchain technology is taking the world by storm. Blockchain with its decentralized, transparent and secure nature has emerged as a disruptive technology for the next generation of numerous industrial applications. One of them is Cloud of Things enabled by the combination of cloud computing and Internet of Things. In this context, blockchain provides innovative solutions to address challenges in Cloud of Things in terms of decentralization, data privacy and network security, while Cloud of Things offer elasticity and scalability functionalities to improve the efficiency of blockchain operations. Therefore, a novel paradigm of blockchain and Cloud of Things integration, called BCoT, has been widely regarded as a promising enabler for a wide range of application scenarios. In this paper, we present a state-of-the-art review on the BCoT integration to provide general readers with an overview of the BCoT in various aspects, including background knowledge, motivation, and integrated architecture. Particularly, we also provide an in-depth survey of BCoT applications in different use-case domains such as smart healthcare, smart city, smart transportation and smart industry. Then, we review the recent BCoT developments with the emerging blockchain and cloud platforms, services, and research projects. Finally, some important research challenges and future directions are highlighted to spur further research in this promising area.

cs.CR↗

arXiv2020

Privacy-Preserved Task Offloading in Mobile Blockchain with Deep Reinforcement Learning

Blockchain technology with its secure, transparent and decentralized nature has been recently employed in many mobile applications. However, the mining process in mobile blockchain requires high computational and storage capability of mobile devices, which would hinder blockchain applications in mobile systems. To meet this challenge, we propose a mobile edge computing (MEC) based blockchain network where multi-mobile users (MUs) act as miners to offload their mining tasks to a nearby MEC server via wireless channels. Specially, we formulate task offloading and user privacy preservation as a joint optimization problem which is modelled as a Markov decision process, where our objective is to minimize the long-term system offloading costs and maximize the privacy levels for all blockchain users. We first propose a reinforcement learning (RL)-based offloading scheme which enables MUs to make optimal offloading decisions based on blockchain transaction states and wireless channel qualities between MUs and MEC server. To further improve the offloading performances for larger-scale blockchain scenarios, we then develop a deep RL algorithm by using deep Q-network which can efficiently solve large state space without any prior knowledge of the system dynamics. Simulation results show that the proposed RL-based offloading schemes significantly enhance user privacy, and reduce the energy consumption as well as computation latency with minimum offloading costs in comparison with the benchmark offloading schemes.

eess.SP↗

arXiv2020

Control of Walking Assist Exoskeleton with Time-delay Based on the Prediction of Plantar Force

Many kinds of lower-limb exoskeletons were developed for walking assistance. However, when controlling these exoskeletons, time-delay due to the computation time and the communication delays is still a general problem. In this research, we propose a novel method to prevent the time-delay when controlling a walking assist exoskeleton by predicting the future plantar force and walking status. By using Long Short-Term Memory and a fully-connected network, the plantar force can be predicted using only data measured by inertial measurement unit sensors, not only during the walking period but also at the start and end of walking. From the predicted plantar force, the walking status and the desired assistance timing can also be determined. By considering the time-delay and sending the control commands beforehand, the exoskeleton can be moved precisely on the desired assistance timing. In experiments, the prediction accuracy of the plantar force and the assistance timing are confirmed. The performance of the proposed method is also evaluated by using the trained model to control the exoskeleton.

cs.RO↗

arXiv2020

RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network

Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. Without directly interactive with training examples, the generative model can be fully used to estimate the underlying distribution of an original dataset while the discriminative model can examine the quality of the generated samples by comparing the label values with the training examples. However, when GANs are applied on sensitive or private training examples, such as medical or financial records, it is still probable to divulge individuals' sensitive and private information. To mitigate this information leakage and construct a private GAN, in this work we propose a Rényi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random noises on the value of the loss function during training. Moreover, we derive the analytical results of the total privacy loss under the subsampling method and cumulated iterations, which show its effectiveness on the privacy budget allocation. In addition, in order to mitigate the negative impact brought by the injecting noise, we enhance the proposed algorithm by adding an adaptive noise tuning step, which will change the volume of added noise according to the testing accuracy. Through extensive experimental results, we verify that the proposed algorithm can achieve a better privacy level while producing high-quality samples compared with a benchmark DP-GAN scheme based on noise perturbation on training gradients.

cs.LG↗

arXiv2020

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training

Graph representation learning has emerged as a powerful technique for addressing real-world problems. Various downstream graph learning tasks have benefited from its recent developments, such as node classification, similarity search, and graph classification. However, prior arts on graph representation learning focus on domain specific problems and train a dedicated model for each graph dataset, which is usually non-transferable to out-of-domain data. Inspired by the recent advances in pre-training from natural language processing and computer vision, we design Graph Contrastive Coding (GCC) -- a self-supervised graph neural network pre-training framework -- to capture the universal network topological properties across multiple networks. We design GCC's pre-training task as subgraph instance discrimination in and across networks and leverage contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations. We conduct extensive experiments on three graph learning tasks and ten graph datasets. The results show that GCC pre-trained on a collection of diverse datasets can achieve competitive or better performance to its task-specific and trained-from-scratch counterparts. This suggests that the pre-training and fine-tuning paradigm presents great potential for graph representation learning.

cs.LG↗

arXiv2020

Enhancements of the 3GPP LTE-Advanced and the Prized Asset: Dynamic TDD Transmissions

In this paper, we perform a survey on new Third Generation Partnership Project (3GPP) Long Term Evolution-Advanced (LTE-Advanced) enhancements,covering the technologies recently adopted by the 3GPP in LTE Release 11 and those being discussed in LTE Release 12. In more details, we introduce the latest enhancements on carrier aggregation (CA), multiple-input multiple-output (MIMO) and coordinated multi-point (CoMP) as well as three-dimensional (3D) MIMO. Moreover, considering that network nodes will become very diverse in the future, and thus with heterogeneous network (HetNet) being a key feature of LTE-Advanced networks, we also discuss technologies of interest in HetNet scenarios, e.g., enhanced physical data control channel (ePDCCH), further enhanced inter-cell interference coordination (FeICIC) and small cells, together with energy efficiency concerns. In particular, we pay special attention to one of the most important enhancements in LTE Release 12, i.e., dynamic time division duplex (TDD) transmissions, and present performance results that shed new light on this topic.

cs.IT↗

arXiv2020

On Dynamic Time Division Duplex Transmissions for Small Cell Networks

Motivated by the promising benefits of dynamic Time Division Duplex (TDD), in this paper, we use a unified framework to investigate both the technical issues of applying dynamic TDD in homogeneous small cell networks (HomSCNs), and the feasibility of introducing dynamic TDD into heterogeneous networks (HetNets). First, HomSCNs are analyzed, and a small cell BS scheduler that dynamically and independently schedules DL and UL subframes is presented, such that load balancing between the DL and the UL traffic can be achieved. Moreover, the effectiveness of various inter-link interference mitigation (ILIM) schemes as well as their combinations, is systematically investigated and compared. Besides, the interesting possibility of partial interference cancellation (IC) is also explored. Second,based on the proposed schemes, the joint operation of dynamic TDD together with cell range expansion (CRE) and almost blank subframe (ABS) in HetNets is studied. In this regard, scheduling polices in small cells and an algorithm to derive the appropriate macrocell traffic off-load and ABS duty cycle under dynamic TDD operation are proposed. Moreover, the full IC and the partial IC schemes are investigated for dynamic TDD in HetNets. The user equipment (UE) packet throughput performance of the proposed/discussed schemes is benchmarked using system-level simulations.

cs.IT↗

arXiv2020

Understanding Negative Sampling in Graph Representation Learning

Graph representation learning has been extensively studied in recent years. Despite its potential in generating continuous embeddings for various networks, both the effectiveness and efficiency to infer high-quality representations toward large corpus of nodes are still challenging. Sampling is a critical point to achieve the performance goals. Prior arts usually focus on sampling positive node pairs, while the strategy for negative sampling is left insufficiently explored. To bridge the gap, we systematically analyze the role of negative sampling from the perspectives of both objective and risk, theoretically demonstrating that negative sampling is as important as positive sampling in determining the optimization objective and the resulted variance. To the best of our knowledge, we are the first to derive the theory and quantify that the negative sampling distribution should be positively but sub-linearly correlated to their positive sampling distribution. With the guidance of the theory, we propose MCNS, approximating the positive distribution with self-contrast approximation and accelerating negative sampling by Metropolis-Hastings. We evaluate our method on 5 datasets that cover extensive downstream graph learning tasks, including link prediction, node classification and personalized recommendation, on a total of 19 experimental settings. These relatively comprehensive experimental results demonstrate its robustness and superiorities.

cs.LG↗

arXiv2020

Probabilistic Caching for Small-Cell Networks with Terrestrial and Aerial Users

The support for aerial users has become the focus of recent 3GPP standardizations of 5G, due to their high maneuverability and flexibility for on-demand deployment. In this paper, probabilistic caching is studied for ultra-dense small-cell networks with terrestrial and aerial users, where a dynamic on-off architecture is adopted under a sophisticated path loss model incorporating both line-of-sight and non-line-of-sight transmissions. Generally, this paper focuses on the successful download probability (SDP) of user equipments (UEs) from small-cell base stations (SBSs) that cache the requested files under various caching strategies. To be more specific, the SDP is first analyzed using stochastic geometry theory, by considering the distribution of such two-tier UEs and SBSs as Homogeneous Poisson Point Processes. Second, an optimized caching strategy (OCS) is proposed to maximize the average SDP. Third, the performance limits of the average SDP are developed for the popular caching strategy (PCS) and the uniform caching strategy (UCS). Finally, the impacts of the key parameters, such as the SBS density, the cache size, the exponent of Zipf distribution and the height of aerial user, are investigated on the average SDP. The analytical results indicate that the UCS outperforms the PCS if the SBSs are sufficiently dense, while the PCS is better than the UCS if the exponent of Zipf distribution is large enough. Furthermore, the proposed OCS is superior to both the UCS and PCS.

eess.SP↗