Search Results for author: Ping Wang

Found 67 papers, 21 papers with code

RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias

no code implementations23 Sep 2023 Hao Cheng, Jinhao Duan, Hui Li, Lyutianyang Zhang, Jiahang Cao, Ping Wang, Jize Zhang, Kaidi Xu, Renjing Xu

Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP).

ArcGPT: A Large Language Model Tailored for Real-world Archival Applications

no code implementations27 Jul 2023 Shitou Zhang, Jingrui Hou, Siyuan Peng, Zuchao Li, Qibiao Hu, Ping Wang

Ultimately, ArcGPT aims to better serve the archival community, aiding archivists in their crucial role of preserving and harnessing our collective information and knowledge.

Language Modelling Large Language Model +1

Multiobjective Hydropower Reservoir Operation Optimization with Transformer-Based Deep Reinforcement Learning

no code implementations11 Jul 2023 Rixin Wu, Ran Wang, Jie Hao, Qiang Wu, Ping Wang

Due to shortage of water resources and increasing water demands, the joint operation of multireservoir systems for balancing power generation, ecological protection, and the residential water supply has become a critical issue in hydropower management.

Management reinforcement-learning

AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness

no code implementations24 May 2023 Zihui Wu, Haichang Gao, Bingqian Zhou, Ping Wang

To tackle this problem, we propose a simple but effective strategy called Adversarial Function Matching (AdvFunMatch), which aims to match distributions for all data points within the $\ell_p$-norm ball of the training data, in accordance with consistent teaching.

Adversarial Robustness Knowledge Distillation

Two-shot Video Object Segmentation

1 code implementation CVPR 2023 Kun Yan, Xiao Li, Fangyun Wei, Jinglu Wang, Chenbin Zhang, Ping Wang, Yan Lu

The underlying idea is to generate pseudo labels for unlabeled frames during training and to optimize the model on the combination of labeled and pseudo-labeled data.

Pseudo Label Semantic Segmentation +3

Conformal Loss-Controlling Prediction

no code implementations6 Jan 2023 Di Wang, Ping Wang, Zhong Ji, Xiaojun Yang, Hongyue Li

Conformal prediction is a learning framework controlling prediction coverage of prediction sets, which can be built on any learning algorithm for point prediction.

Conformal Prediction Weather Forecasting

Solving Coupled Differential Equation Groups Using PINO-CDE

1 code implementation1 Oct 2022 Wenhao Ding, Qing He, Hanghang Tong, Qingjing Wang, Ping Wang

This framework integrates engineering dynamics and deep learning technologies and may reveal a new concept for CDEs solving and uncertainty propagation.

Event Detection Explorer: An Interactive Tool for Event Detection Exploration

no code implementations26 Apr 2022 Wenlong Zhang, Bhagyashree Ingale, Hamza Shabir, Tianyi Li, Tian Shi, Ping Wang

ED Explorer consists of an interactive web application, an API, and an NLP toolkit, which can help both domain experts and non-experts to better understand the ED task.

Event Detection

Localization Distillation for Object Detection

1 code implementation12 Apr 2022 Zhaohui Zheng, Rongguang Ye, Qibin Hou, Dongwei Ren, Ping Wang, WangMeng Zuo, Ming-Ming Cheng

Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.

Knowledge Distillation object-detection +1

Multi-Label Clinical Time-Series Generation via Conditional GAN

1 code implementation10 Apr 2022 Chang Lu, Chandan K. Reddy, Ping Wang, Dong Nie, Yue Ning

In this work, we propose a Multi-label Time-series GAN (MTGAN) to generate EHR and simultaneously improve the quality of uncommon disease generation.

Representation Learning Time Series +1

A Deep Reinforcement Learning-Based Caching Strategy for IoT Networks with Transient Data

no code implementations16 Mar 2022 Hongda Wu, Ali Nasehzadeh, Ping Wang

In this work, we propose a DRL-based caching scheme that improves the cache hit rate and reduces energy consumption of the IoT networks, in the meanwhile, taking data freshness and limited lifetime of IoT data into account.

reinforcement-learning Reinforcement Learning (RL)

Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation

no code implementations4 Feb 2022 Jizong Peng, Ping Wang, Marco Pedersoli, Christian Desrosiers

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data.

Contrastive Learning Image Segmentation +3

Semantics-Preserved Distortion for Personal Privacy Protection in Information Management

no code implementations4 Jan 2022 Jiajia Li, Letian Peng, Ping Wang, Zuchao Li, Xueyi Li, Hai Zhao

As the model training on information from users is likely to invade personal privacy, many methods have been proposed to block the learning and memorizing of the sensitive data in raw texts.

Constituency Parsing Federated Learning +5

Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes

no code implementations1 Aug 2021 Ping Wang, Tian Shi, Khushbu Agarwal, Sutanay Choudhury, Chandan K. Reddy

On the other hand, the aspects, entity and context, limit the answers by node-specific information and lead to higher precision and lower recall.

Knowledge Base Question Answering Machine Reading Comprehension

Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework

no code implementations31 Jul 2021 Li Ding, Yongwei Wang, Xin Ding, Kaiwen Yuan, Ping Wang, Hua Huang, Z. Jane Wang

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images.

Adversarial Defense Image Classification +1

Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels

1 code implementation NeurIPS 2021 Jizong Peng, Ping Wang, Chrisitian Desrosiers, Marco Pedersoli

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e. g., image classification.

Contrastive Learning Image Classification +3

Context-aware virtual adversarial training for anatomically-plausible segmentation

no code implementations12 Jul 2021 Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers

Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions.

CNN Retrieval based Unsupervised Metric Learning for Near-Duplicated Video Retrieval

no code implementations30 May 2021 Hao Cheng, Ping Wang, Chun Qi

As important data carriers, the drastically increasing number of multimedia videos often brings many duplicate and near-duplicate videos in the top results of search.

Metric Learning Re-Ranking +2

Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data

1 code implementation14 May 2021 Hongda Wu, Ping Wang

In this paper, we proposed Optimal Aggregation algorithm for better aggregation, which finds out the optimal subset of local updates of participating nodes in each global round, by identifying and excluding the adverse local updates via checking the relationship between the local gradient and the global gradient.

Federated Learning

An Improved Discriminative Optimization for 3D Rigid Point Cloud Registration

no code implementations18 Apr 2021 Jia Wang, Ping Wang, Biao Li, Ruigang Fu, Junzheng Wu

The Discriminative Optimization (DO) algorithm has been proved much successful in 3D point cloud registration.

Point Cloud Registration

RAGA: Relation-aware Graph Attention Networks for Global Entity Alignment

2 code implementations1 Mar 2021 Renbo Zhu, Meng Ma, Ping Wang

Entity alignment (EA) is the task to discover entities referring to the same real-world object from different knowledge graphs (KGs), which is the most crucial step in integrating multi-source KGs.

Entity Alignment Graph Attention +1

Tunable ferroelectricity in hBN intercalated twisted double-layer graphene

no code implementations24 Feb 2021 Yibo Wang, Siqi Jiang, Jingkuan Xiao, Xiaofan Cai, Di Zhang, Ping Wang, Guodong Ma, Yaqing Han, Jiabei Huang, Kenji Watanabe, Takashi Taniguchi, Alexander S. Mayorov, Geliang Yu

Van der Waals (vdW) assembly of two-dimensional materials has been long recognized as a powerful tool to create unique systems with properties that cannot be found in natural compounds.

Mesoscale and Nanoscale Physics Materials Science

Localization Distillation for Dense Object Detection

2 code implementations CVPR 2022 Zhaohui Zheng, Rongguang Ye, Ping Wang, Dongwei Ren, WangMeng Zuo, Qibin Hou, Ming-Ming Cheng

Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement.

Dense Object Detection Knowledge Distillation +1

Millimeter Wave MIMO based Depth Maps for Wireless Virtual and Augmented Reality

no code implementations11 Feb 2021 Abdelrahman Taha, Qi Qu, Sam Alex, Ping Wang, William L. Abbott, Ahmed Alkhateeb

Accounting for the constraints on these systems, we develop a comprehensive framework for constructing accurate and high-resolution depth maps using mmWave systems.

Ambient Backscatter-Assisted Wireless-Powered Relaying

no code implementations2 Feb 2021 Xiao Lu, Dusit Niyato, Hai Jiang, Ekram Hossain, Ping Wang

With different mode selection protocols, we characterize the success probability and ergodic capacity of a dual-hop relaying system with the hybrid relay in the field of randomly located ambient transmitters.

Information Theory Networking and Internet Architecture Information Theory

Few-shot Image Classification with Multi-Facet Prototypes

no code implementations1 Feb 2021 Kun Yan, Zied Bouraoui, Ping Wang, Shoaib Jameel, Steven Schockaert

The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples.

Classification Few-Shot Image Classification +2

Fast-Convergent Federated Learning with Adaptive Weighting

no code implementations1 Dec 2020 Hongda Wu, Ping Wang

With extensive experiments performed in Pytorch and PySyft, we show that FL training with FedAdp can reduce the number of communication rounds by up to 54. 1% on MNIST dataset and up to 45. 4% on FashionMNIST dataset, as compared to FedAvg algorithm.

Federated Learning

A Learning-based Optimization Algorithm:Image Registration Optimizer Network

1 code implementation23 Nov 2020 Jia Wang, Ping Wang, Biao Li, Yinghui Gao, Siyi Zhao

As the search space of registration is usually non-convex, the optimization algorithm, which aims to search the best transformation parameters, is a challenging step.

Image Registration

Self-paced and self-consistent co-training for semi-supervised image segmentation

1 code implementation31 Oct 2020 Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers

Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy.

Image Segmentation Semantic Segmentation

Classical-noise-free sensing based on quantum correlation measurement

no code implementations22 Sep 2020 Ping Wang, Chong Chen, Renbao Liu

An intriguing question is: Can the quantum nature (quantumness) of sensors and targets be exploited to enable schemes that are not possible for classical probes or classical targets?

Quantum Physics

An Interpretable and Uncertainty Aware Multi-Task Framework for Multi-Aspect Sentiment Analysis

2 code implementations18 Sep 2020 Tian Shi, Ping Wang, Chandan K. Reddy

In addition, we also propose an Attention-driven Keywords Ranking (AKR) method, which can automatically discover aspect keywords and aspect-level opinion keywords from the review corpus based on the attention weights.

Extract Aspect Multi-Task Learning +3

A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection

1 code implementation18 Sep 2020 Tian Shi, Liuqing Li, Ping Wang, Chandan K. Reddy

However, recent deep learning-based topic models, specifically aspect-based autoencoder, suffer from several problems, such as extracting noisy aspects and poorly mapping aspects discovered by models to the aspects of interest.

Contrastive Learning Topic Models

A Bidirectional Tree Tagging Scheme for Joint Medical Relation Extraction

no code implementations31 Aug 2020 Xukun Luo, Weijie Liu, Meng Ma, Ping Wang

In this paper, inspired by the tree-like relation structures in the medical text, we propose a novel scheme called Bidirectional Tree Tagging (BiTT) to form the medical relation triples into two two binary trees and convert the trees into a word-level tags sequence.

Medical Relation Extraction Relation Extraction

Effects of local decoherence on quantum critical metrology

no code implementations11 Aug 2020 Chong Chen, Ping Wang, Ren-Bao Liu

94, 047201 (2005)] on the critical behaviors of the noisy Ising model, which shows that the universality class of the quantum criticality is modified by the decoherence, we find that the standard quantum limit is recovered by the single-particle decoherence, which is equivalent to local quantum measurement conducted by the environment and destroys the many-body entanglement in the ground state at the quantum critical point.

Quantum Physics

Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks

1 code implementation22 Jul 2020 Ping Wang, Khushbu Agarwal, Colby Ham, Sutanay Choudhury, Chandan K. Reddy

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node.

Link Prediction Representation Learning +1

Electromagnetic form factors of octet baryons with the nonlocal chiral effective theory

no code implementations25 May 2020 Mingyang Yang, Ping Wang

The electromagnetic form factors of octet baryons are investigated with the nonlocal chiral effective theory.

High Energy Physics - Phenomenology

Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation

6 code implementations7 May 2020 Zhaohui Zheng, Ping Wang, Dongwei Ren, Wei Liu, Rongguang Ye, QinGhua Hu, WangMeng Zuo

In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.

Clustering Instance Segmentation +4

Corpus-level and Concept-based Explanations for Interpretable Document Classification

1 code implementation24 Apr 2020 Tian Shi, Xuchao Zhang, Ping Wang, Chandan K. Reddy

In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights.

Classification Decision Making +2

Optimal Pricing of Internet of Things: A Machine Learning Approach

no code implementations14 Feb 2020 Mohammad Abu Alsheikh, Dinh Thai Hoang, Dusit Niyato, Derek Leong, Ping Wang, Zhu Han

For service bundles, the subscription fee and data sizes of the grouped IoT services are optimized to maximize the total profit of cooperative service providers.

BIG-bench Machine Learning

Toward an Automated Auction Framework for Wireless Federated Learning Services Market

no code implementations13 Dec 2019 Yutao Jiao, Ping Wang, Dusit Niyato, Bin Lin, Dong In Kim

In this paper, we propose an auction based market model for incentivizing data owners to participate in federated learning.

Computer Science and Game Theory

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

20 code implementations19 Nov 2019 Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, Dongwei Ren

By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e. g., YOLO v3, SSD and Faster RCNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric.

object-detection Object Detection +1

Platoon trajectories generation: A unidirectional interconnected LSTM-based car following model

no code implementations25 Oct 2019 Yangxin Lin, Ping Wang, Yang Zhou, Fan Ding, Chen Wang, Huachun Tan

However, the traffic micro-simulation accuracy of car following models in a platoon level, especially during traffic oscillations, still needs to be enhanced.

K-BERT: Enabling Language Representation with Knowledge Graph

2 code implementations arXiv 2019 Weijie Liu, Peng Zhou, Zhe Zhao, Zhiruo Wang, Qi Ju, Haotang Deng, Ping Wang

For machines to achieve this capability, we propose a knowledge-enabled language representation model (K-BERT) with knowledge graphs (KGs), in which triples are injected into the sentences as domain knowledge.

Knowledge Graphs

A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification

no code implementations26 Aug 2019 Rui Li, Zhibin Pan, Yang Wang, Ping Wang

In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification.

Classification General Classification +1

Text-to-SQL Generation for Question Answering on Electronic Medical Records

1 code implementation28 Jul 2019 Ping Wang, Tian Shi, Chandan K. Reddy

In this paper, we tackle these challenges by developing a deep learning based TRanslate-Edit Model for Question-to-SQL (TREQS) generation, which adapts the widely used sequence-to-sequence model to directly generate the SQL query for a given question, and further performs the required edits using an attentive-copying mechanism and task-specific look-up tables.

Information Retrieval Question Answering +2

LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization

1 code implementation NAACL 2019 Tian Shi, Ping Wang, Chandan K. Reddy

Neural abstractive text summarization (NATS) has received a lot of attention in the past few years from both industry and academia.

Abstractive Text Summarization

A Method for Expressing and Displaying the Vehicle Behavior Distribution in Maintenance Work Zones

no code implementations25 Apr 2019 Qun Yang, Zhepu Xu, Saravanan Gurupackiam, Ping Wang

By this method, how vehicles travel through maintenance work zones, and how different vehicle behaviours distribute in maintenance work zones can be displayed intuitively on maps, which is a novel traffic characteristic and can shed light to maintenance work zone related researches such as safety assessment and design method.

Layout Design

Joint Service Pricing and Cooperative Relay Communication for Federated Learning

no code implementations29 Nov 2018 Shaohan Feng, Dusit Niyato, Ping Wang, Dong In Kim, Ying-Chang Liang

However, the learning process of the existing federated learning platforms rely on the direct communication between the model owner, e. g., central cloud or edge server, and the mobile devices for transferring the model update.

Cryptography and Security Computer Science and Game Theory

Applications of Deep Reinforcement Learning in Communications and Networking: A Survey

no code implementations18 Oct 2018 Nguyen Cong Luong, Dinh Thai Hoang, Shimin Gong, Dusit Niyato, Ping Wang, Ying-Chang Liang, Dong In Kim

Reinforcement learning has been efficiently used to enable the network entities to obtain the optimal policy including, e. g., decisions or actions, given their states when the state and action spaces are small.

reinforcement-learning Reinforcement Learning (RL)

Estimate the Warfarin Dose by Ensemble of Machine Learning Algorithms

no code implementations10 Sep 2018 Zhiyuan Ma, Ping Wang, Zehui Gao, Ruobing Wang, Koroush Khalighi

Here, we present novel algorithms using stacked generalization frameworks to estimate the warfarin dose, within which different types of machine learning algorithms function together through a meta-machine learning model to maximize the prediction accuracy.

BIG-bench Machine Learning

Optimal and Low-Complexity Dynamic Spectrum Access for RF-Powered Ambient Backscatter System with Online Reinforcement Learning

no code implementations8 Sep 2018 Nguyen Van Huynh, Dinh Thai Hoang, Diep N. Nguyen, Eryk Dutkiewicz, Dusit Niyato, Ping Wang

To cope with such incomplete knowledge of the environment, we develop a low-complexity online reinforcement learning algorithm that allows the secondary transmitter to "learn" from its decisions and then attain the optimal policy.


Joint Ground and Aerial Package Delivery Services: A Stochastic Optimization Approach

no code implementations14 Aug 2018 Suttinee Sawadsitang, Dusit Niyato, Puay-Siew Tan, Ping Wang

A considerable number of works have studied different aspects of drone package delivery service by a supplier, one of which is delivery planning.

Stochastic Optimization

Adversarial Noise Layer: Regularize Neural Network By Adding Noise

1 code implementation21 May 2018 Zhonghui You, Jinmian Ye, Kunming Li, Zenglin Xu, Ping Wang

In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL) and its efficient version called Class Adversarial Noise Layer (CANL), which are able to significantly improve CNN's generalization ability by adding carefully crafted noise into the intermediate layer activations.

A Survey on Consensus Mechanisms and Mining Strategy Management in Blockchain Networks

no code implementations7 May 2018 Wenbo Wang, Dinh Thai Hoang, Peizhao Hu, Zehui Xiong, Dusit Niyato, Ping Wang, Yonggang Wen, Dong In Kim

This survey is motivated by the lack of a comprehensive literature review on the development of decentralized consensus mechanisms in blockchain networks.

Cryptography and Security

Optimal Stochastic Package Delivery Planning with Deadline: A Cardinality Minimization in Routing

no code implementations28 Feb 2018 Suttinee Sawadsitang, Siwei Jiang, Dusit Niyato, Ping Wang

Vehicle Routing Problem with Private fleet and common Carrier (VRPPC) has been proposed to help a supplier manage package delivery services from a single depot to multiple customers.

Decentralized Caching for Content Delivery Based on Blockchain: A Game Theoretic Perspective

no code implementations23 Jan 2018 Wenbo Wang, Dusit Niyato, Ping Wang, Amir Leshem

In this paper, we propose a decentralized framework of proactive caching in a hierarchical wireless network based on blockchains.

Networking and Internet Architecture

Cyberattack Detection in Mobile Cloud Computing: A Deep Learning Approach

no code implementations16 Dec 2017 Khoi Khac Nguyen, Dinh Thai Hoang, Dusit Niyato, Ping Wang, Diep Nguyen, Eryk Dutkiewicz

With the rapid growth of mobile applications and cloud computing, mobile cloud computing has attracted great interest from both academia and industry.

Cloud Computing

Optimal Auction For Edge Computing Resource Management in Mobile Blockchain Networks: A Deep Learning Approach

no code implementations8 Nov 2017 Nguyen Cong Luong, Zehui Xiong, Ping Wang, Dusit Niyato

However, a mechanism needs to be designed for edge resource allocation to maximize the revenue for the Edge Computing Service Provider and to ensure incentive compatibility and individual rationality is still open.

Computer Science and Game Theory

Machine Learning for Survival Analysis: A Survey

no code implementations15 Aug 2017 Ping Wang, Yan Li, Chandan K. Reddy

We hope that this paper will provide a more thorough understanding of the recent advances in survival analysis and offer some guidelines on applying these approaches to solve new problems that arise in applications with censored data.

BIG-bench Machine Learning Survival Analysis

Efficient Background Modeling Based on Sparse Representation and Outlier Iterative Removal

no code implementations23 Jan 2014 Linhao Li, Ping Wang, QinGhua Hu, Sijia Cai

A cyclic iteration process is then proposed to extract the background from the discriminative frame set.

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