Search Results for author: He Li

Found 22 papers, 7 papers with code

Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark

1 code implementation12 Nov 2023 Wenke Huang, Mang Ye, Zekun Shi, Guancheng Wan, He Li, Bo Du, Qiang Yang

In this survey, we provide a systematic overview of the important and recent developments of research on federated learning.

Fairness Federated Learning +1

An Efficient Imbalance-Aware Federated Learning Approach for Wearable Healthcare with Autoregressive Ratio Observation

no code implementations23 Oct 2023 Wenhao Yan, He Li, Kaoru Ota, Mianxiong Dong

Widely available healthcare services are now getting popular because of advancements in wearable sensing techniques and mobile edge computing.

Edge-computing Federated Learning

Constrained CycleGAN for Effective Generation of Ultrasound Sector Images of Improved Spatial Resolution

1 code implementation2 Sep 2023 Xiaofei Sun, He Li, Wei-Ning Lee

In vitro phantom results demonstrate that CCycleGAN successfully generates images with improved spatial resolution as well as higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared with benchmarks.

Image Generation Motion Estimation +1

When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA

1 code implementation13 Aug 2023 Hongxiang Fan, Hao Chen, Liam Castelli, Zhiqiang Que, He Li, Kenneth Long, Wayne Luk

Bayesian Neural Networks (BayesNNs) have demonstrated their capability of providing calibrated prediction for safety-critical applications such as medical imaging and autonomous driving.

Autonomous Driving

Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent

no code implementations30 Dec 2022 Xi Chen, Zehua Lai, He Li, Yichen Zhang

With the fast development of big data, it has been easier than before to learn the optimal decision rule by updating the decision rule recursively and making online decisions.

Decision Making Multi-Armed Bandits

LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics

1 code implementation28 Sep 2022 Zhiqiang Que, Hongxiang Fan, Marcus Loo, He Li, Michaela Blott, Maurizio Pierini, Alexander Tapper, Wayne Luk

This work presents a novel reconfigurable architecture for Low Latency Graph Neural Network (LL-GNN) designs for particle detectors, delivering unprecedented low latency performance.

Random Ensemble Reinforcement Learning for Traffic Signal Control

no code implementations10 Mar 2022 Ruijie Qi, Jianbin Huang, He Li, Qinglin Tan, Longji Huang, Jiangtao Cui

Moreover, we introduce the Update-To-Data (UTD) ratio to control the number of data reuses to improve the problem of low data utilization.

Ensemble Learning reinforcement-learning +1

AnomMAN: Detect Anomaly on Multi-view Attributed Networks

no code implementations8 Jan 2022 Ling-Hao Chen, He Li, Wanyuan Zhang, Jianbin Huang, Xiaoke Ma, Jiangtao Cui, Ning li, Jaesoo Yoo

It remains a challenging task to jointly consider all different kinds of interactions and detect anomalous instances on multi-view attributed networks.

Anomaly Detection

Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator

no code implementations24 Nov 2021 Hongxiang Fan, Martin Ferianc, Zhiqiang Que, He Li, Shuanglong Liu, Xinyu Niu, Wayne Luk

Recent advances in algorithm-hardware co-design for deep neural networks (DNNs) have demonstrated their potential in automatically designing neural architectures and hardware designs.

DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction

no code implementations19 Oct 2021 He Li, Shiyu Zhang, Xuejiao Li, Liangcai Su, Hongjie Huang, Duo Jin, Linghao Chen, Jianbing Huang, Jaesoo Yoo

Detectors with high coverage have direct and far-reaching benefits for road users in route planning and avoiding traffic congestion, but utilizing these data presents unique challenges including: the dynamic temporal correlation, and the dynamic spatial correlation caused by changes in road conditions.

Traffic Prediction

An Efficient Network Design for Face Video Super-resolution

no code implementations28 Sep 2021 Feng Yu, He Li, Sige Bian, Yongming Tang

We construct a dataset consisting entirely of face video sequences for network training and evaluation, and conduct hyper-parameter optimization in our experiments.

SSIM Video Super-Resolution

Real-Time Super-Resolution System of 4K-Video Based on Deep Learning

1 code implementation12 Jul 2021 Yanpeng Cao, Chengcheng Wang, Changjun Song, Yongming Tang, He Li

In order to pursue faster VSR processing ability up to 4K resolution, this paper tries to choose lightweight network structure and efficient upsampling method to reduce the computation required by EGVSR network under the guarantee of high visual quality.

Video Super-Resolution

Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods

no code implementations5 Feb 2021 Xi Chen, Zehua Lai, He Li, Yichen Zhang

We first present the asymptotic distribution for the Polyak-Ruppert-averaging type Kiefer-Wolfowitz (AKW) estimators, whose asymptotic covariance matrices depend on the distribution of search directions and the function-value query complexity.

Stochastic Optimization valid

Distributed Estimation for Principal Component Analysis: an Enlarged Eigenspace Analysis

no code implementations5 Apr 2020 Xi Chen, Jason D. Lee, He Li, Yun Yang

To abandon this eigengap assumption, we consider a new route in our analysis: instead of exactly identifying the top-$L$-dim eigenspace, we show that our estimator is able to cover the targeted top-$L$-dim population eigenspace.

Quantifying Intrinsic Uncertainty in Classification via Deep Dirichlet Mixture Networks

no code implementations11 Jun 2019 Qingyang Wu, He Li, Lexin Li, Zhou Yu

With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning.

Classification General Classification +1

Adversarial Examples: Attacks on Machine Learning-based Malware Visualization Detection Methods

no code implementations5 Aug 2018 Xinbo Liu, Yapin Lin, He Li, Jiliang Zhang

As the threat of malicious software (malware) becomes urgently serious, automatic malware detection techniques have received increasing attention recently, where the machine learning (ML)-based visualization detection plays a significant role. However, this leads to a fundamental problem whether such detection methods can be robust enough against various potential attacks. Even though ML algorithms show superiority to conventional ones in malware detection in terms of high efficiency and accuracy, this paper demonstrates that such ML-based malware detection methods are vulnerable to adversarial examples (AE) attacks. We propose the first AE-based attack framework, named Adversarial Texture Malware Perturbation Attacks (ATMPA), based on the gradient descent or L-norm optimization method. By introducing tiny perturbations on the transformed dataset, ML-based malware detection methods completely fail. The experimental results on the MS BIG malware dataset show that a small interference can reduce the detection rate of convolutional neural network (CNN), support vector machine (SVM) and random forest(RF)-based malware detectors down to 0 and the attack transferability can achieve up to 88. 7% and 74. 1% on average in different ML-based detection methods.

Cryptography and Security

Robust Video Content Alignment and Compensation for Clear Vision Through the Rain

no code implementations24 Apr 2018 Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li

Extensive evaluations show that advantage of up to 5dB is achieved on the scene restoration PSNR over state-of-the-art methods, and the advantage is especially obvious with highly complex and dynamic scenes.

Rain Removal

Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework

no code implementations CVPR 2018 Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li

Visual inspection shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.

Rain Removal

Cannot find the paper you are looking for? You can Submit a new open access paper.