Search Results for author: Peng Yang

Found 52 papers, 9 papers with code

Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

1 code implementation CVPR 2023 Fei Du, Peng Yang, Qi Jia, Fengtao Nan, Xiaoting Chen, Yun Yang

In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while reducing the training skills and overhead.

Long-tail Learning

Reducing Idleness in Financial Cloud via Multi-objective Evolutionary Reinforcement Learning based Load Balancer

1 code implementation5 May 2023 Peng Yang, Laoming Zhang, Haifeng Liu, Guiying Li

In recent years, various companies started to shift their data services from traditional data centers onto cloud.

Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence

no code implementations23 Mar 2023 Chaoqun You, Kun Guo, Gang Feng, Peng Yang, Tony Q. S. Quek

With the obtained FL hyperparameters and resource allocation, we design a MAML-based FL algorithm, called Automated Federated Learning (AutoFL), that is able to conduct fast adaptation and convergence.

Federated Learning Meta-Learning

Extraction of cropland field parcels with high resolution remote sensing using multi-task learning

1 code implementation European Journal of Remote Sensing 2023 Leilei Xu, Peng Yang, Juanjuan Yu, Fei Peng, Jia Xu, Shiran Song &Yongxing Wu

Parcel-level farmland information contains rich spatial distribution and boundary details, which is crucial for digital agriculture and agricultural resource surveys.

Edge Detection Management +1

Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding

no code implementations31 Jan 2023 Lan Tang, Xiaxi Li, Jinyuan Zhang, Guiying Li, Peng Yang, Ke Tang

The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE.

Atari Games reinforcement-learning +1

Performance Analysis and Enhancement of Beamforming Training in 802.11ad

no code implementations2 Jan 2023 Wen Wu, Nan Cheng, Ning Zhang, Peng Yang, Khalid Aldubaikhy, Xuemin, Shen

Since the derived BF training efficiency is an implicit function, to reveal the relationship between system parameters and BF training performance, we also derive an approximate expression of BF training efficiency.

Cost-Effective Two-Stage Network Slicing for Edge-Cloud Orchestrated Vehicular Networks

no code implementations31 Dec 2022 Wen Wu, Kaige Qu, Peng Yang, Ning Zhang, Xuemin, Shen, Weihua Zhuang

Since the problem is NP-hard due to coupled network planning and network operation stages, we develop a Two timescAle netWork Slicing (TAWS) algorithm by collaboratively integrating reinforcement learning (RL) and optimization methods, which can jointly make network planning and operation decisions.

Reinforcement Learning (RL) Stochastic Optimization

Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning

no code implementations31 Dec 2022 Wen Wu, Peng Yang, Weiting Zhang, Conghao Zhou, Xuemin, Shen

Specifically, sampling rate adaption, inference task offloading and edge computing resource allocation are jointly considered to minimize the average service delay while guaranteeing the long-term accuracy requirements of different inference services.

Edge-computing General Reinforcement Learning +2

Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis

no code implementations13 Dec 2022 Chunyu Qiang, Peng Yang, Hao Che, Xiaorui Wang, Zhongyuan Wang

In order to improve the style extraction ability of the reference encoder, a style invariant and contrastive data augmentation method is proposed.

Data Augmentation Speech Synthesis +1

Securer and Faster Privacy-Preserving Distributed Machine Learning

no code implementations17 Nov 2022 Hongxiao Wang, Zoe L. Jiang, Yanmin Zhao, Siu-Ming Yiu, Peng Yang, Zejiu Tan, Bohan Jin, Shiyuan Xu, Shimin Pan

We prove the correctness and security of our decryption protocol and compare the efficiency and accuracy between using Taylor polynomials of Sigmoid and our proposed function as an activation function.

Privacy Preserving regression

Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation

no code implementations17 Nov 2022 Chunyu Qiang, Peng Yang, Hao Che, Jinba Xiao, Xiaorui Wang, Zhongyuan Wang

In this paper we propose a simple back-translation-style data augmentation method for mandarin Chinese polyphone disambiguation, utilizing a large amount of unlabeled text data.

Data Augmentation Machine Translation +3

CU-Net: LiDAR Depth-Only Completion With Coupled U-Net

1 code implementation26 Oct 2022 YuFei Wang, Yuchao Dai, Qi Liu, Peng Yang, Jiadai Sun, Bo Li

We find that existing depth-only methods can obtain satisfactory results in the areas where the measurement points are almost accurate and evenly distributed (denoted as normal areas), while the performance is limited in the areas where the foreground and background points are overlapped due to occlusion (denoted as overlap areas) and the areas where there are no measurement points around (denoted as blank areas) since the methods have no reliable input information in these areas.

KeypartX: Graph-based Perception (Text) Representation

1 code implementation23 Sep 2022 Peng Yang

However, big data is a double-edged sword which is big in volume but unstructured in format.


Defending Backdoor Attacks on Vision Transformer via Patch Processing

no code implementations24 Jun 2022 Khoa D. Doan, Yingjie Lao, Peng Yang, Ping Li

We first examine the vulnerability of ViTs against various backdoor attacks and find that ViTs are also quite vulnerable to existing attacks.

Backdoor Attack Inductive Bias

One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching

1 code implementation CVPR 2022 Khoa D. Doan, Peng Yang, Ping Li

However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses.

Quantization Retrieval

Energy-Sensitive Trajectory Design and Restoration Areas Allocation for UAV-Enabled Grassland Restoration

no code implementations10 Apr 2022 Dongbin Jiao, Lingyu Wang, Peng Yang, Weibo Yang, Yu Peng, Zhanhuan Shang, Fengyuan Ren

As a result, the maximization of restoration areas turns out to be a composite of a trajectory design problem and an areas allocation problem that are highly coupled.

Combinatorial Optimization Incremental Learning +1

Over-the-Air Federated Learning via Second-Order Optimization

1 code implementation29 Mar 2022 Peng Yang, Yuning Jiang, Ting Wang, Yong Zhou, Yuanming Shi, Colin N. Jones

To address this issue, in this paper, we instead propose a novel over-the-air second-order federated optimization algorithm to simultaneously reduce the communication rounds and enable low-latency global model aggregation.

Federated Learning

Machine Learning Empowered Intelligent Data Center Networking: A Survey

no code implementations28 Feb 2022 Bo Li, Ting Wang, Peng Yang, Mingsong Chen, Shui Yu, Mounir Hamdi

To support the needs of ever-growing cloud-based services, the number of servers and network devices in data centers is increasing exponentially, which in turn results in high complexities and difficulties in network optimization.

BIG-bench Machine Learning Management

Mitigating Forgetting in Online Continual Learning with Neuron Calibration

no code implementations NeurIPS 2021 Haiyan Yin, Peng Yang, Ping Li

Though recent studies have achieved remarkable progress in improving the online continual learning performance empowered by the deep neural networks-based models, many of today's approaches still suffer a lot from catastrophic forgetting, a persistent challenge for continual learning.

Continual Learning

Networking of Internet of UAVs: Challenges and Intelligent Approaches

no code implementations13 Nov 2021 Peng Yang, Xianbin Cao, Tony Q. S. Quek, Dapeng Oliver Wu

Internet of unmanned aerial vehicle (I-UAV) networks promise to accomplish sensing and transmission tasks quickly, robustly, and cost-efficiently via effective cooperation among UAVs.

Approaching the Transient Stability Boundary of a Power System: Theory and Applications

no code implementations26 Sep 2021 Peng Yang, Feng Liu, Wei Wei, Zhaojian Wang

Estimating the stability boundary is a fundamental and challenging problem in transient stability studies.

Active Reinforcement Learning over MDPs

no code implementations5 Aug 2021 Qi Yang, Peng Yang, Ke Tang

This paper proposes a framework of Active Reinforcement Learning (ARL) over MDPs to improve generalization efficiency in a limited resource by instance selection.

reinforcement-learning Reinforcement Learning (RL)

Augmented Synchronization of Power Systems

no code implementations24 Jun 2021 Peng Yang, Feng Liu, Tao Liu, David J. Hill

Here, we formulate the empirical wisdom by the concept of augmented synchronization and aim to bridge such a theory-practice gap.

Feeling of Presence Maximization: mmWave-Enabled Virtual Reality Meets Deep Reinforcement Learning

no code implementations3 Jun 2021 Peng Yang, Tony Q. S. Quek, Jingxuan Chen, Chaoqun You, Xianbin Cao

This paper investigates the problem of providing ultra-reliable and energy-efficient virtual reality (VR) experiences for wireless mobile users.

reinforcement-learning Reinforcement Learning (RL)

Robust Dynamic Network Embedding via Ensembles

3 code implementations30 May 2021 Chengbin Hou, Guoji Fu, Peng Yang, Zheng Hu, Shan He, Ke Tang

It is natural to ask if existing DNE methods can perform well for an input dynamic network without smooth changes.

Network Embedding

Mitigating Forgetting in Online Continual Learning with Neuron Calibration

no code implementations NeurIPS 2021 Haiyan Yin, Peng Yang, Ping Li

Though recent studies have achieved remarkable progress in improving the online continual learning performance empowered by the deep neural networks-based models, many of today's approaches still suffer a lot from catastrophic forgetting, a persistent challenge for continual learning.

Continual Learning

Measurement methods of radial flow in relativistic heavy-ion collisions

no code implementations4 Mar 2021 Peng Yang, Lin Li, Zhiming Li, Mingmei Xu, Yeyin Zhao, Yuanfang Wu

Radial flow can be directly extracted from the azimuthal distribution of mean transverse rapidity.

Nuclear Theory High Energy Physics - Phenomenology Nuclear Experiment

Fresh, Fair and Energy-Efficient Content Provision in a Private and Cache-Enabled UAV Network

no code implementations25 Feb 2021 Peng Yang, Kun Guo, Xing Xi, Tony Q. S. Quek, Xianbin Cao, Chenxi Liu

Particularly, we first propose to decompose the sequential decision problem into multiple repeated optimization subproblems via a Lyapunov technique.

Networking and Internet Architecture Signal Processing

Robust Watermarking for Deep Neural Networks via Bi-Level Optimization

no code implementations ICCV 2021 Peng Yang, Yingjie Lao, Ping Li

Deep neural networks (DNNs) have become state-of-the-art in many application domains.

Power Control for a URLLC-enabled UAV system incorporated with DNN-Based Channel Estimation

no code implementations14 Nov 2020 Peng Yang, Xing Xi, Tony Q. S. Quek, Xianbin Cao, Jingxuan Chen

This problem is challenging to be solved due to the requirement of analytically tractable channel models and the non-convex characteristic as well.

Deep Reinforcement Learning for Delay-Oriented IoT Task Scheduling in Space-Air-Ground Integrated Network

no code implementations4 Oct 2020 Conghao Zhou, Wen Wu, Hongli He, Peng Yang, Feng Lyu, Nan Cheng, Xuemin, Shen

Our objective is to design a task scheduling policy that minimizes offloading and computing delay of all tasks given the UAV energy capacity constraint.


Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search

no code implementations8 Sep 2020 Hu Zhang, Peng Yang, Yanglong Yu, Mingjia Li, Ke Tang

Evolutionary algorithms (EAs) have been successfully applied to optimize the policies for Reinforcement Learning (RL) tasks due to their exploration ability.

Atari Games reinforcement-learning +1

Few-shots Parallel Algorithm Portfolio Construction via Co-evolution

no code implementations1 Jul 2020 Ke Tang, Shengcai Liu, Peng Yang, Xin Yao

In the context of heuristic search, such a paradigm could be implemented as configuring the parameters of a parallel algorithm portfolio (PAP) based on a set of training problem instances, which is often referred to as PAP construction.

Traveling Salesman Problem

Distributed Primal-Dual Optimization for Online Multi-Task Learning

no code implementations2 Apr 2020 Peng Yang, Ping Li

Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task relatedness.

Multi-Task Learning

Optimal Stochastic and Online Learning with Individual Iterates

no code implementations NeurIPS 2019 Yunwen Lei, Peng Yang, Ke Tang, Ding-Xuan Zhou

In this paper, we propose a theoretically sound strategy to select an individual iterate of the vanilla SCMD, which is able to achieve optimal rates for both convex and strongly convex problems in a non-smooth learning setting.

Sparse Learning

Parallel Exploration via Negatively Correlated Search

no code implementations16 Oct 2019 Peng Yang, Qi Yang, Ke Tang, Xin Yao

Empirical results show that the significant advantages of NCS over the compared state-of-the-art methods can be highly owed to the effective parallel exploration ability.

Atari Games reinforcement-learning +1

Fast mmwave Beam Alignment via Correlated Bandit Learning

no code implementations7 Sep 2019 Wen Wu, Nan Cheng, Ning Zhang, Peng Yang, Weihua Zhuang, Xuemin, Shen

Beam alignment (BA) is to ensure the transmitter and receiver beams are accurately aligned to establish a reliable communication link in millimeter-wave (mmwave) systems.

A Parallel Divide-and-Conquer based Evolutionary Algorithm for Large-scale Optimization

no code implementations6 Dec 2018 Peng Yang, Ke Tang, Xin Yao

Large-scale optimization problems that involve thousands of decision variables have extensively arisen from various industrial areas.

Robust Cost-Sensitive Learning for Recommendation with Implicit Feedback

no code implementations3 Jul 2017 Peng Yang, Peilin Zhao, Xin Gao, Yong liu

Morever, the proposed algorithm can be scaled up to large-sized datasets after a relaxation.

Robust Online Multi-Task Learning with Correlative and Personalized Structures

no code implementations6 Jun 2017 Peng Yang, Peilin Zhao, Xin Gao

Multi-Task Learning (MTL) can enhance a classifier's generalization performance by learning multiple related tasks simultaneously.

Multi-Task Learning

High-dimensional Black-box Optimization via Divide and Approximate Conquer

no code implementations11 Mar 2016 Peng Yang, Ke Tang, Xin Yao

Divide and Conquer (DC) is conceptually well suited to high-dimensional optimization by decomposing a problem into multiple small-scale sub-problems.

Vocal Bursts Intensity Prediction

Supporting Regularized Logistic Regression Privately and Efficiently

no code implementations1 Oct 2015 Wenfa Li, Hongzhe Liu, Peng Yang, Wei Xie

As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on.

BIG-bench Machine Learning Epidemiology +1

Negatively Correlated Search

no code implementations20 Apr 2015 Ke Tang, Peng Yang, Xin Yao

This paper presents a new EA, namely Negatively Correlated Search (NCS), which maintains multiple individual search processes in parallel and models the search behaviors of individual search processes as probability distributions.

Classification and its applications for drug-target interaction identification

no code implementations16 Feb 2015 Jian-Ping Mei, Chee-Keong Kwoh, Peng Yang, Xiao-Li Li

Classification is one of the most popular and widely used supervised learning tasks, which categorizes objects into predefined classes based on known knowledge.

Classification Drug Discovery +1

Microbial community pattern detection in human body habitats via ensemble clustering framework

no code implementations21 Dec 2014 Peng Yang, Xiaoquan Su, Le Ou-Yang, Hon-Nian Chua, Xiao-Li Li, Kang Ning

To obtain a comprehensive view, we propose a novel ensemble clustering framework to mine the structure of microbial community pattern on large-scale metagenomic data.

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