arXiv subjects

Shibo He

Publications and source records attributed to Shibo He.

At least 55 records · Page 3Linked to original sources

arXiv2022

$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling

Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning. Since the discovery that original DARTS will inevitably converge to poor architectures, recent works alleviate this by either designing rule-based architecture selection techniques or incorporating complex regularization techniques, abandoning the simplicity of the original DARTS that selects architectures based on the largest parametric value, namely $α$. Moreover, we find that all the previous attempts only rely on classification labels, hence learning only single modal information and limiting the representation power of the shared network. To this end, we propose to additionally inject semantic information by formulating a patch recovery approach. Specifically, we exploit the recent trending masked image modeling and do not abandon the guidance from the downstream tasks during the search phase. Our method surpasses all previous DARTS variants and achieves state-of-the-art results on CIFAR-10, CIFAR-100, and ImageNet without complex manual-designed strategies.

cs.CV↗

arXiv2022

PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model

Publishing trajectory data (individual's movement information) is very useful, but it also raises privacy concerns. To handle the privacy concern, in this paper, we apply differential privacy, the standard technique for data privacy, together with Markov chain model, to generate synthetic trajectories. We notice that existing studies all use Markov chain model and thus propose a framework to analyze the usage of the Markov chain model in this problem. Based on the analysis, we come up with an effective algorithm PrivTrace that uses the first-order and second-order Markov model adaptively. We evaluate PrivTrace and existing methods on synthetic and real-world datasets to demonstrate the superiority of our method.

cs.CR↗

arXiv2022

Efficient View Path Planning for Autonomous Implicit Reconstruction

Implicit neural representations have shown promising potential for the 3D scene reconstruction. Recent work applies it to autonomous 3D reconstruction by learning information gain for view path planning. Effective as it is, the computation of the information gain is expensive, and compared with that using volumetric representations, collision checking using the implicit representation for a 3D point is much slower. In the paper, we propose to 1) leverage a neural network as an implicit function approximator for the information gain field and 2) combine the implicit fine-grained representation with coarse volumetric representations to improve efficiency. Further with the improved efficiency, we propose a novel informative path planning based on a graph-based planner. Our method demonstrates significant improvements in the reconstruction quality and planning efficiency compared with autonomous reconstructions with implicit and explicit representations. We deploy the method on a real UAV and the results show that our method can plan informative views and reconstruct a scene with high quality.

cs.RO↗

arXiv2022

Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search

Neural Architecture Search (NAS) is a powerful tool for automating effective image processing DNN designing. The ranking has been advocated to design an efficient performance predictor for NAS. The previous contrastive method solves the ranking problem by comparing pairs of architectures and predicting their relative performance. However, it only focuses on the rankings between two involved architectures and neglects the overall quality distributions of the search space, which may suffer generalization issues. A predictor, namely Neural Architecture Ranker (NAR) which concentrates on the global quality tier of specific architecture, is proposed to tackle such problems caused by the local perspective. The NAR explores the quality tiers of the search space globally and classifies each individual to the tier they belong to according to its global ranking. Thus, the predictor gains the knowledge of the performance distributions of the search space which helps to generalize its ranking ability to the datasets more easily. Meanwhile, the global quality distribution facilitates the search phase by directly sampling candidates according to the statistics of quality tiers, which is free of training a search algorithm, e.g., Reinforcement Learning (RL) or Evolutionary Algorithm (EA), thus it simplifies the NAS pipeline and saves the computational overheads. The proposed NAR achieves better performance than the state-of-the-art methods on two widely used datasets for NAS research. On the vast search space of NAS-Bench-101, the NAR easily finds the architecture with top 0.01$\unicode{x2030}$ performance only by sampling. It also generalizes well to different image datasets of NAS-Bench-201, i.e., CIFAR-10, CIFAR-100, and ImageNet-16-120 by identifying the optimal architectures for each of them.

cs.CV↗

arXiv2022

AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation

In an asynchronous federated learning framework, the server updates the global model once it receives an update from a client instead of waiting for all the updates to arrive as in the synchronous setting. This allows heterogeneous devices with varied computing power to train the local models without pausing, thereby speeding up the training process. However, it introduces the stale model problem, where the newly arrived update was calculated based on a set of stale weights that are older than the current global model, which may hurt the convergence of the model. In this paper, we present an asynchronous federated learning framework with a proposed adaptive weight aggregation algorithm, referred to as AsyncFedED. To the best of our knowledge this aggregation method is the first to take the staleness of the arrived gradients, measured by the Euclidean distance between the stale model and the current global model, and the number of local epochs that have been performed, into account. Assuming general non-convex loss functions, we prove the convergence of the proposed method theoretically. Numerical results validate the effectiveness of the proposed AsyncFedED in terms of the convergence rate and model accuracy compared to the existing methods for three considered tasks.

cs.LG↗

arXiv2022

Semantic-preserved Communication System for Highly Efficient Speech Transmission

Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years. In contrast to traditional wireless communication methods that focus on the transmission of abstract symbols, semantic communication approaches attempt to achieve better transmission efficiency by only sending the semantic-related information of the source data. In this paper, we consider semantic-oriented speech transmission which transmits only the semantic-relevant information over the channel for the speech recognition task, and a compact additional set of semantic-irrelevant information for the speech reconstruction task. We propose a novel end-to-end DL-based transceiver which extracts and encodes the semantic information from the input speech spectrums at the transmitter and outputs the corresponding transcriptions from the decoded semantic information at the receiver. For the speech to speech transmission, we further include a CTC alignment module that extracts a small number of additional semantic-irrelevant but speech-related information for the better reconstruction of the original speech signals at the receiver. The simulation results confirm that our proposed method outperforms current methods in terms of the accuracy of the predicted text for the speech to text transmission and the quality of the recovered speech signals for the speech to speech transmission, and significantly improves transmission efficiency. More specifically, the proposed method only sends 16% of the amount of the transmitted symbols required by the existing methods while achieving about 10% reduction in WER for the speech to text transmission. For the speech to speech transmission, it results in an even more remarkable improvement in terms of transmission efficiency with only 0.2% of the amount of the transmitted symbols required by the existing method.

eess.AS↗

arXiv2022

Semantic-aware Speech to Text Transmission with Redundancy Removal

eess.AS↗

arXiv2021

FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices

With the increased penetration and proliferation of Internet of Things (IoT) devices, there is a growing trend towards distributing the power of deep learning (DL) across edge devices rather than centralizing it in the cloud. This development enables better privacy preservation, real-time responses, and user-specific models. To deploy deep and complex models to edge devices with limited resources, model partitioning of deep neural networks (DNN) model is necessary, and has been widely studied. However, most of the existing literature only considers distributing the inference model while still relying centralized cloud infrastructure to generate this model through training. In this paper, we propose FTPipeHD, a novel DNN training framework that trains DNN models across distributed heterogeneous devices with fault tolerance mechanism. To accelerate the training with time-varying computing power of each device, we optimize the partition points dynamically according to real-time computing capacities. We also propose a novel weight redistribution approach that replicates the weights to both the neighboring nodes and the central node periodically, which combats the failure of multiple devices during training while incurring limited communication cost. Our numerical results demonstrate that FTPipeHD is 6.8x faster in training than the state of the art method when the computing capacity of the best device is 10x greater than the worst one. It is also shown that the proposed method is able to accelerate the training even with the existence of device failures.

cs.LG↗

arXiv2021

Fairness-aware Outlier Ensemble

Outlier ensemble methods have shown outstanding performance on the discovery of instances that are significantly different from the majority of the data. However, without the awareness of fairness, their applicability in the ethical scenarios, such as fraud detection and judiciary judgement system, could be degraded. In this paper, we propose to reduce the bias of the outlier ensemble results through a fairness-aware ensemble framework. Due to the lack of ground truth in the outlier detection task, the key challenge is how to mitigate the degradation in the detection performance with the improvement of fairness. To address this challenge, we define a distance measure based on the output of conventional outlier ensemble techniques to estimate the possible cost associated with detection performance degradation. Meanwhile, we propose a post-processing framework to tune the original ensemble results through a stacking process so that we can achieve a trade off between fairness and detection performance. Detection performance is measured by the area under ROC curve (AUC) while fairness is measured at both group and individual level. Experiments on eight public datasets are conducted. Results demonstrate the effectiveness of the proposed framework in improving fairness of outlier ensemble results. We also analyze the trade-off between AUC and fairness.

cs.LG↗

arXiv2020

PrivSyn: Differentially Private Data Synthesis

In differential privacy (DP), a challenging problem is to generate synthetic datasets that efficiently capture the useful information in the private data. The synthetic dataset enables any task to be done without privacy concern and modification to existing algorithms. In this paper, we present PrivSyn, the first automatic synthetic data generation method that can handle general tabular datasets (with 100 attributes and domain size $>2^{500}$). PrivSyn is composed of a new method to automatically and privately identify correlations in the data, and a novel method to generate sample data from a dense graphic model. We extensively evaluate different methods on multiple datasets to demonstrate the performance of our method.

cs.CR↗

arXiv2020

Universal Urban Spreading Pattern of COVID-19 and Its Underlying Mechanism

Currently, the global situation of COVID-19 is aggravating, pressingly calling for efficient control and prevention measures. Understanding spreading pattern of COVID-19 has been widely recognized as a vital step for implementing non-pharmaceutical measures. Previous studies investigated such an issue in large-scale (e.g., inter-country or inter-state) scenarios while urban spreading pattern still remains an open issue. Here, we fill this gap by leveraging the trajectory data of 197,808 smartphone users (including 17,808 anonymous confirmed cases) in 9 cities in China. We find a universal spreading pattern in all cities: the spatial distribution of confirmed cases follows a power-law-like model and the spreading centroid is time-invariant. Moreover, we reveal that human mobility in a city drives the spatialtemporal spreading process: long average travelling distance results in a high growth rate of spreading radius and wide spatial diffusion of confirmed cases. With such insight, we adopt Kendall model to simulate urban spreading of COVID-19 that can well fit the real spreading process. Our results unveil the underlying mechanism behind the spatial-temporal urban evolution of COVID-19, and can be used to evaluate the performance of mobility restriction policies implemented by many governments and to estimate the evolving spreading situation of COVID-19.

physics.soc-ph↗

arXiv2020

PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection

Vision-based dynamic pedestrian intrusion detection (PID), judging whether pedestrians intrude an area-of-interest (AoI) by a moving camera, is an important task in mobile surveillance. The dynamically changing AoIs and a number of pedestrians in video frames increase the difficulty and computational complexity of determining whether pedestrians intrude the AoI, which makes previous algorithms incapable of this task. In this paper, we propose a novel and efficient multi-task deep neural network, PIDNet, to solve this problem. PIDNet is mainly designed by considering two factors: accurately segmenting the dynamically changing AoIs from a video frame captured by the moving camera and quickly detecting pedestrians from the generated AoI-contained areas. Three efficient network designs are proposed and incorporated into PIDNet to reduce the computational complexity: 1) a special PID task backbone for feature sharing, 2) a feature cropping module for feature cropping, and 3) a lighter detection branch network for feature compression. In addition, considering there are no public datasets and benchmarks in this field, we establish a benchmark dataset to evaluate the proposed network and give the corresponding evaluation metrics for the first time. Experimental results show that PIDNet can achieve 67.1% PID accuracy and 9.6 fps inference speed on the proposed dataset, which serves as a good baseline for the future vision-based dynamic PID study.

cs.CV↗

arXiv2020

Discrimination universally determines reconstruction of multiplex networks

Network reconstruction is fundamental to understanding the dynamical behaviors of the networked systems. Many systems, modeled by multiplex networks with various types of interactions, display an entirely different dynamical behavior compared to the corresponding aggregated network. In many cases, unfortunately, only the aggregated topology and partial observations of the network layers are available, raising an urgent demand for reconstructing multiplex networks. We fill this gap by developing a mathematical and computational tool based on the Expectation-Maximization framework to reconstruct multiplex layer structures. The reconstruction accuracy depends on the various factors, such as partial observation and network characteristics, limiting our ability to predict and allocate observations. Surprisingly, by using a mean-field approximation, we discovered that a discrimination indicator that integrates all these factors universally determines the accuracy of reconstruction. This discovery enables us to design the optimal strategies to allocate the fixed budget for deriving the partial observations, promoting the optimal reconstruction of multiplex networks. To further evaluate the performance of our method, we predict beside structure also dynamical behaviors on the multiplex networks, including percolation, random walk, and spreading processes. Finally, applying our method on empirical multiplex networks drawn from biological, transportation, and social domains, corroborate the theoretical analysis.

physics.soc-ph↗

arXiv2020

You foot the bill! Attacking NFC with passive relays

Imagine when you line up in a store, the person in front of you can make you pay her bill by using a passive wearable device that forces a scan of your credit card without your awareness. An important assumption of today's Near-field Communication (NFC) enabled cards is the limited communication range between the commercial reader and the NFC cards -- a distance below 5~cm. Previous approaches to attacking this assumption effectively use mobile phones and active relays to enlarge the communication range, in order to attack the NFC cards. However, these approaches require a power supply at the adversary side, and can be easily localized when mobile phones or active relays transmit NFC signals. We propose ReCoil, a system that uses wearable passive relays to attack NFC cards by expanding the communication range to 49.6 centimeters, a ten-fold improvement over its intended commercial distance. ReCoil is a magnetically coupled resonant wireless power transfer system, which optimizes the energy transfer by searching the optimal geometry parameters. Specifically, we first narrow down the feasible area reasonably and design the ReCoil-Ant Colony Algorithm such that the relays absorb the maximum energy from the reader. In order to reroute the signal to pass over the surface of human body, we then design a half waist band by carefully analyzing the impact of the distance and orientation between two coils on the mutual inductance. Then, three more coils are added to the system to keep enlarging the communication range. Finally, extensive experiment results validate our analysis, showing that our passive relays composed of common copper wires and tunable capacitors expand the range of NFC attacks to 49.6 centimeters.

cs.CR↗

arXiv2019

A Tensor-Based Framework for Studying Eigenvector Multicentrality in Multilayer Networks

Centrality is widely recognized as one of the most critical measures to provide insight in the structure and function of complex networks. While various centrality measures have been proposed for single-layer networks, a general framework for studying centrality in multilayer networks (i.e., multicentrality) is still lacking. In this study, a tensor-based framework is introduced to study eigenvector multicentrality, which enables the quantification of the impact of interlayer influence on multicentrality, providing a systematic way to describe how multicentrality propagates across different layers. This framework can leverage prior knowledge about the interplay among layers to better characterize multicentrality for varying scenarios. Two interesting cases are presented to illustrate how to model multilayer influence by choosing appropriate functions of interlayer influence and design algorithms to calculate eigenvector multicentrality. This framework is applied to analyze several empirical multilayer networks, and the results corroborate that it can quantify the influence among layers and multicentrality of nodes effectively.

physics.soc-ph↗

arXiv2017

LEPA: Incentivizing Long-term Privacy-preserving Data Aggregation in Crowdsensing

In this paper, we study the incentive mechanism design for real-time data aggregation, which holds a large spectrum of crowdsensing applications. Despite extensive studies on static incentive mechanisms, none of these are applicable to real-time data aggregation due to their incapability of maintaining PUs' long-term participation. We emphasize that, to maintain PUs' long-term participation, it is of significant importance to protect their privacy as well as to provide them a desirable cumulative compensation. Thus motivated, in this paper, we propose LEPA, an efficient incentive mechanism to stimulate long-term participation in real-time data aggregation. Specifically, we allow PUs to preserve their privacy by reporting noisy data, the impact of which on the aggregation accuracy is quantified with proper privacy and accuracy measures. Then, we provide a framework that jointly optimizes the incentive schemes in different time slots to ensure desirable cumulative compensation for PUs and thereby prevent PUs from leaving the system halfway. Considering PUs' strategic behaviors and combinatorial nature of the sensing tasks, we propose a computationally efficient on-line auction with close-to-optimal performance in presence of NP-hardness of winner user selection. We further show that the proposed on-line auction satisfies desirable properties of truthfulness and individual rationality. The performance of LEPA is validated by both theoretical analysis and extensive simulations.

cs.GT↗

arXiv2017

REAP: An Efficient Incentive Mechanism for Reconciling Aggregation Accuracy and Individual Privacy in Crowdsensing

Incentive mechanism plays a critical role in privacy-aware crowdsensing. Most previous studies on co-design of incentive mechanism and privacy preservation assume a trustworthy fusion center (FC). Very recent work has taken steps to relax the assumption on trustworthy FC and allows participatory users (PUs) to add well calibrated noise to their raw sensing data before reporting them, whereas the focus is on the equilibrium behavior of data subjects with binary data. Making a paradigm shift, this paper aim to quantify the privacy compensation for continuous data sensing while allowing FC to directly control PUs. There are two conflicting objectives in such scenario: FC desires better quality data in order to achieve higher aggregation accuracy whereas PUs prefer adding larger noise for higher privacy-preserving levels (PPLs). To achieve a good balance therein, we design an efficient incentive mechanism to REconcile FC's Aggregation accuracy and individual PU's data Privacy (REAP). Specifically, we adopt the celebrated notion of differential privacy to measure PUs' PPLs and quantify their impacts on FC's aggregation accuracy. Then, appealing to Contract Theory, we design an incentive mechanism to maximize FC's aggregation accuracy under a given budget. The proposed incentive mechanism offers different contracts to PUs with different privacy preferences, by which FC can directly control PUs. It can further overcome the information asymmetry, i.e., the FC typically does not know each PU's precise privacy preference. We derive closed-form solutions for the optimal contracts in both complete information and incomplete information scenarios. Further, the results are generalized to the continuous case where PUs' privacy preferences take values in a continuous domain. Extensive simulations are provided to validate the feasibility and advantages of our proposed incentive mechanism.

cs.GT↗

arXiv2017

Re-DPoctor: Real-time health data releasing with w-day differential privacy

Wearable devices enable users to collect health data and share them with healthcare providers for improved health service. Since health data contain privacy-sensitive information, unprotected data release system may result in privacy leakage problem. Most of the existing work use differential privacy for private data release. However, they have limitations in healthcare scenarios because they do not consider the unique features of health data being collected from wearables, such as continuous real-time collection and pattern preservation. In this paper, we propose Re-DPoctor, a real-time health data releasing scheme with $w$-day differential privacy where the privacy of health data collected from any consecutive $w$ days is preserved. We improve utility by using a specially-designed partition algorithm to protect the health data patterns. Meanwhile, we improve privacy preservation by applying newly proposed adaptive sampling technique and budget allocation method. We prove that Re-DPoctor satisfies $w$-day differential privacy. Experiments on real health data demonstrate that our method achieves better utility with strong privacy guarantee than existing state-of-the-art methods.

cs.CR↗