Search Results for author: Jing Yang

Found 94 papers, 25 papers with code

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

97 code implementations CVPR 2019 Jiankang Deng, Jia Guo, Jing Yang, Niannan Xue, Irene Kotsia, Stefanos Zafeiriou

Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability.

 Ranked #1 on Face Verification on Labeled Faces in the Wild (using extra training data)

Face Generation Face Identification +2

Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC

2 code implementations28 Mar 2022 Xiang An, Jiankang Deng, Jia Guo, Ziyong Feng, Xuhan Zhu, Jing Yang, Tongliang Liu

In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.

Face Recognition Face Verification

Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC

1 code implementation CVPR 2022 Xiang An, Jiankang Deng, Jia Guo, Ziyong Feng, Xuhan Zhu, Jing Yang, Tongliang Liu

In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.

Face Recognition

Unicom: Universal and Compact Representation Learning for Image Retrieval

2 code implementations12 Apr 2023 Xiang An, Jiankang Deng, Kaicheng Yang, Jaiwei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes.

 Ranked #1 on Image Retrieval on SOP (using extra training data)

Image Retrieval Metric Learning +4

Pre-training strategies and datasets for facial representation learning

2 code implementations30 Mar 2021 Adrian Bulat, Shiyang Cheng, Jing Yang, Andrew Garbett, Enrique Sanchez, Georgios Tzimiropoulos

Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e. g. face recognition, facial landmark localization etc.)

3D Face Reconstruction 3D Facial Landmark Localization +11

DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis

1 code implementation20 Dec 2023 Yuming Gu, You Xie, Hongyi Xu, Guoxian Song, Yichun Shi, Di Chang, Jing Yang, Linjie Luo

The rendering view is then manipulated with a novel conditional control module that interprets the camera pose by watching a condition image of a crossed subject from the same view.

Denoising

ALIP: Adaptive Language-Image Pre-training with Synthetic Caption

1 code implementation ICCV 2023 Kaicheng Yang, Jiankang Deng, Xiang An, Jiawei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning.

Representation Learning Retrieval +1

PMET: Precise Model Editing in a Transformer

1 code implementation17 Aug 2023 Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, Jie Yu

To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns.

General Knowledge Model Editing

A Mountain-Shaped Single-Stage Network for Accurate Image Restoration

1 code implementation9 May 2023 Hu Gao, Jing Yang, Ying Zhang, Ning Wang, Jingfan Yang, Depeng Dang

Image restoration is the task of aiming to obtain a high-quality image from a corrupt input image, such as deblurring and deraining.

Deblurring Image Deblurring +2

Knowledge Distillation Meets Open-Set Semi-Supervised Learning

1 code implementation13 May 2022 Jing Yang, Xiatian Zhu, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

The key idea is that we leverage the teacher's classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions.

Face Recognition Knowledge Distillation

Adaptive Scenario Discovery for Crowd Counting

1 code implementation6 Dec 2018 Xingjiao Wu, Yingbin Zheng, Hao Ye, Wenxin Hu, Jing Yang, Liang He

Crowd counting, i. e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications.

Crowd Counting

Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT

1 code implementation24 Jul 2018 Jing Yang, Biao Zhang, Yue Qin, Xiangwen Zhang, Qian Lin, Jinsong Su

Although neural machine translation(NMT) yields promising translation performance, it unfortunately suffers from over- and under-translation is- sues [Tu et al., 2016], of which studies have become research hotspots in NMT.

Machine Translation NMT +1

Light Sampling Field and BRDF Representation for Physically-based Neural Rendering

1 code implementation ICLR 2023 Jing Yang, Hanyuan Xiao, Wenbin Teng, Yunxuan Cai, Yajie Zhao

Extensive experiments showcase the quality and efficiency of our PBR face skin shader, indicating the effectiveness of our proposed lighting and material representations.

Inverse Rendering Lightfield +2

Federated Multi-armed Bandits with Personalization

1 code implementation25 Feb 2021 Chengshuai Shi, Cong Shen, Jing Yang

A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with personalization.

Federated Learning Multi-Armed Bandits

Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing

1 code implementation30 Dec 2021 Shice Liu, Shitao Lu, Hongyi Xu, Jing Yang, Shouhong Ding, Lizhuang Ma

However, the improvement is still limited by two issues: 1) It is difficult to perfectly map all faces to a shared feature space.

Disentanglement Domain Generalization +1

A Real-Time Deep Network for Crowd Counting

1 code implementation16 Feb 2020 Xiaowen Shi, Xin Li, Caili Wu, Shuchen Kong, Jing Yang, Liang He

Automatic analysis of highly crowded people has attracted extensive attention from computer vision research.

Crowd Counting

DED: Diagnostic Evidence Distillation for acne severity grading on face images

1 code implementation Expert Systems with Applications 2023 Yi Lin, Jingchi Jiang, Dongxin Chen, Zhaoyang Ma, Yi Guan, Xiguang Liu, Haiyan You, Jing Yang

In this study, we propose an acne diagnosis method, Diagnostic Evidence Distillation (DED), that suitably adapts the characteristics of acne diagnosis and can be applied to diagnose under different acne criteria.

 Ranked #1 on Acne Severity Grading on ACNE04 (Accuracy metric)

Acne Severity Grading Image Classification +2

Few-shot Learning for Multi-modal Social Media Event Filtering

1 code implementation16 Nov 2022 José Nascimento, João Phillipe Cardenuto, Jing Yang, Anderson Rocha

To the best of our knowledge, this dataset is the first of its kind in event filtering that focuses on protests in multi-modal social media data, with most of the text in Portuguese.

Few-Shot Learning

Best Arm Identification for Prompt Learning under a Limited Budget

1 code implementation15 Feb 2024 Chengshuai Shi, Kun Yang, Jing Yang, Cong Shen

Based on this connection, a general framework TRIPLE (besT aRm Identification for Prompt LEarning) is proposed to harness the power of BAI-FB in prompt learning systematically.

Instruction Following Multi-Armed Bandits

The (1+$λ$) Evolutionary Algorithm with Self-Adjusting Mutation Rate

no code implementations7 Apr 2017 Benjamin Doerr, Christian Gießen, Carsten Witt, Jing Yang

We propose a new way to self-adjust the mutation rate in population-based evolutionary algorithms in discrete search spaces.

Evolutionary Algorithms

Cost-Aware Learning and Optimization for Opportunistic Spectrum Access

no code implementations11 Apr 2018 Chao Gan, Ruida Zhou, Jing Yang, Cong Shen

Our objective is to understand how the costs and reward of the actions would affect the optimal behavior of the user in both offline and online settings, and design the corresponding opportunistic spectrum access strategies to maximize the expected cumulative net reward (i. e., reward-minus-cost).

Adaptive Compressive Tracking via Online Vector Boosting Feature Selection

no code implementations21 Apr 2015 Qingshan Liu, Jing Yang, Kaihua Zhang, Yi Wu

Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency, but it cannot well deal with the large scale target appearance variations due to its data-independent random projection matrix that results in less discriminative features.

feature selection

Optimal Parameter Choices via Precise Black-Box Analysis

no code implementations9 Jul 2018 Benjamin Doerr, Carola Doerr, Jing Yang

It has been observed that some working principles of evolutionary algorithms, in particular, the influence of the parameters, cannot be understood from results on the asymptotic order of the runtime, but only from more precise results.

Evolutionary Algorithms

Runtime Analysis for Self-adaptive Mutation Rates

no code implementations30 Nov 2018 Benjamin Doerr, Carsten Witt, Jing Yang

We propose and analyze a self-adaptive version of the $(1,\lambda)$ evolutionary algorithm in which the current mutation rate is part of the individual and thus also subject to mutation.

Online Learning with Diverse User Preferences

no code implementations23 Jan 2019 Chao Gan, Jing Yang, Ruida Zhou, Cong Shen

We aim to show that when the user preferences are sufficiently diverse and each arm can be optimal for certain users, the O(log T) regret incurred by exploring the sub-optimal arms under the standard stochastic MAB setting can be reduced to a constant.

Edge-Aware Deep Image Deblurring

no code implementations4 Jul 2019 Zhichao Fu, Tianlong Ma, Yingbin Zheng, Hao Ye, Jing Yang, Liang He

In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring.

Deblurring Edge Detection +1

Fast Video Crowd Counting with a Temporal Aware Network

no code implementations4 Jul 2019 Xingjiao Wu, Baohan Xu, Yingbin Zheng, Hao Ye, Jing Yang, Liang He

Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting.

Crowd Counting

Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition

no code implementations16 Sep 2019 Jingkai Weng, Yujiang Ding, Chengbo Hu, Xue-Feng Zhu, Bin Liang, Jing Yang, Jianchun Cheng

Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements.

Handwritten Digit Recognition Object Recognition

Cascaded Detail-Preserving Networks for Super-Resolution of Document Images

no code implementations25 Nov 2019 Zhichao Fu, Yu Kong, Yingbin Zheng, Hao Ye, Wenxin Hu, Jing Yang, Liang He

The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results.

Image Super-Resolution Optical Character Recognition (OCR)

Decentralized Multi-player Multi-armed Bandits with No Collision Information

no code implementations29 Feb 2020 Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang

The decentralized stochastic multi-player multi-armed bandit (MP-MAB) problem, where the collision information is not available to the players, is studied in this paper.

Multi-Armed Bandits

Stochastic Linear Contextual Bandits with Diverse Contexts

no code implementations5 Mar 2020 Weiqiang Wu, Jing Yang, Cong Shen

In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits.

Multi-Armed Bandits

Knowledge distillation via adaptive instance normalization

no code implementations9 Mar 2020 Jing Yang, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos

To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from the teacher to the student.

Knowledge Distillation Model Compression

Adaptive 3D Face Reconstruction from a Single Image

no code implementations8 Jul 2020 Kun Li, Jing Yang, Nianhong Jiao, Jinsong Zhang, Yu-Kun Lai

3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses.

3D Face Reconstruction Pose Estimation

Knowledge distillation via softmax regression representation learning

no code implementations ICLR 2021 Jing Yang, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos

We advocate for a method that optimizes the output feature of the penultimate layer of the student network and hence is directly related to representation learning.

Knowledge Distillation Model Compression +2

DARE: AI-based Diver Action Recognition System using Multi-Channel CNNs for AUV Supervision

no code implementations16 Nov 2020 Jing Yang, James P. Wilson, Shalabh Gupta

With the growth of sensing, control and robotic technologies, autonomous underwater vehicles (AUVs) have become useful assistants to human divers for performing various underwater operations.

Action Recognition Autonomous Driving

OrgMining 2.0: A Novel Framework for Organizational Model Mining from Event Logs

no code implementations24 Nov 2020 Jing Yang, Chun Ouyang, Wil M. P. van der Aalst, Arthur H. M. ter Hofstede, Yang Yu

We demonstrate the feasibility of this framework by proposing an approach underpinned by the framework for organizational model discovery, and also conduct experiments on real-life event logs to discover and evaluate organizational models.

Model Discovery

Experimental demonstration of superresolution of partially coherent light sources using parity sorting

no code implementations2 Feb 2021 S. A. Wadood, Yiyu Zhou, Jing Yang, Kevin Liang, M. A. Alonso, X. -F. Qian, T. Malhotra, S. M. Hashemi Rafsanjani, Andrew N. Jordan, Robert W. Boyd, A. N. Vamivakas

Analyses based on quantum metrology have shown that the ability to localize the positions of two incoherent point sources can be significantly enhanced through the use of mode sorting.

Optics Quantum Physics

Magnetic field generation from bubble collisions during first-order phase transition

no code implementations2 Feb 2021 Jing Yang, Ligong Bian

We study the magnetic fields generation from the cosmological first-order electroweak phase transition.

Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology High Energy Physics - Theory

Document Layout Analysis via Dynamic Residual Feature Fusion

no code implementations7 Apr 2021 Xingjiao Wu, Ziling Hu, Xiangcheng Du, Jing Yang, Liang He

The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval.

Document Layout Analysis Optical Character Recognition +2

Robust Kalman filter-based dynamic state estimation of natural gas pipeline networks

no code implementations26 Feb 2021 Liang Chen, Peng Jin, Jing Yang, Yang Li, Yi Song

To obtain the accurate transient states of the big scale natural gas pipeline networks under the bad data and non-zero mean noises conditions, a robust Kalman filter-based dynamic state estimation method is proposed using the linearized gas pipeline transient flow equations in this paper.

Multi-Spectrally Constrained Transceiver Design against Signal-Dependent Interference

no code implementations10 May 2021 Jing Yang, Augusto Aubry, Antonio De Maio, Xianxiang Yu, Guolong Cui

This paper focuses on the joint synthesis of constant envelope transmit signal and receive filter aimed at optimizing radar performance in signal-dependent interference and spectrally contested-congested environments.

Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting

no code implementations23 Jun 2021 Yuehai Chen, Jing Yang, Dong Zhang, Kun Zhang, Badong Chen, Shaoyi Du

More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity.

Crowd Counting

Variational Prototype Learning for Deep Face Recognition

no code implementations CVPR 2021 Jiankang Deng, Jia Guo, Jing Yang, Alexandros Lattas, Stefanos Zafeiriou

Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.

Face Recognition

Deep-learning-based Hyperspectral imaging through a RGB camera

no code implementations12 Jul 2021 Xinyu Gao, Tianlang Wang, Jing Yang, Jinchao Tao, Yanqing Qiu, Yanlong Meng, Banging Mao, Pengwei Zhou, Yi Li

Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection.

Scalable Fact-checking with Human-in-the-Loop

1 code implementation22 Sep 2021 Jing Yang, Didier Vega-Oliveros, Tais Seibt, Anderson Rocha

Researchers have been investigating automated solutions for fact-checking in a variety of fronts.

Fact Checking

Federated Linear Contextual Bandits

no code implementations NeurIPS 2021 Ruiquan Huang, Weiqiang Wu, Jing Yang, Cong Shen

This paper presents a novel federated linear contextual bandits model, where individual clients face different $K$-armed stochastic bandits coupled through common global parameters.

Multi-Armed Bandits

Duck swarm algorithm: a novel swarm intelligence algorithm

no code implementations27 Dec 2021 Mengjian Zhang, Guihua Wen, Jing Yang

A swarm intelligence-based optimization algorithm, named Duck Swarm Algorithm (DSA), is proposed in this paper.

Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis

no code implementations25 Jan 2022 Luwei Xiao, Xingjiao Wu, Wen Wu, Jing Yang, Liang He

This paper proposes a Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion.

Multimodal Sentiment Analysis

On Federated Learning with Energy Harvesting Clients

no code implementations12 Feb 2022 Cong Shen, Jing Yang, Jie Xu

Catering to the proliferation of Internet of Things devices and distributed machine learning at the edge, we propose an energy harvesting federated learning (EHFL) framework in this paper.

Federated Learning Scheduling

Transformer-based Cross-Modal Recipe Embeddings with Large Batch Training

no code implementations10 May 2022 Jing Yang, Junwen Chen, Keiji Yanai

In this paper, we present a cross-modal recipe retrieval framework, Transformer-based Network for Large Batch Training (TNLBT), which is inspired by ACME~(Adversarial Cross-Modal Embedding) and H-T~(Hierarchical Transformer).

Contrastive Learning Image Generation +2

The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022

no code implementations IWSLT (ACL) 2022 Weitai Zhang, Zhongyi Ye, Haitao Tang, Xiaoxi Li, Xinyuan Zhou, Jing Yang, Jianwei Cui, Dan Liu, Junhua Liu, LiRong Dai

This paper describes USTC-NELSLIP’s submissions to the IWSLT 2022 Offline Speech Translation task, including speech translation of talks from English to German, English to Chinese and English to Japanese.

Translation

Provable Benefit of Multitask Representation Learning in Reinforcement Learning

no code implementations13 Jun 2022 Yuan Cheng, Songtao Feng, Jing Yang, Hong Zhang, Yingbin Liang

To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask RL for both upstream and downstream tasks.

Offline RL reinforcement-learning +2

Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation

no code implementations21 Jun 2022 Yuehai Chen, Jing Yang, Badong Chen, Shaoyi Du

Thus, CNN could locate and estimate crowds accurately in low-density regions, while it is hard to properly perceive the densities in high-density regions.

Crowd Counting

Unified BERT for Few-shot Natural Language Understanding

no code implementations24 Jun 2022 Junyu Lu, Ping Yang, Ruyi Gan, Jing Yang, Jiaxing Zhang

Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas.

Natural Language Understanding

Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL

no code implementations28 Jun 2022 Ruiquan Huang, Jing Yang, Yingbin Liang

In particular, we consider the scenario where a safe baseline policy is known beforehand, and propose a unified Safe reWard-frEe ExploraTion (SWEET) framework.

Safe Exploration

PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks

no code implementations COLING 2022 Pengwei Zhan, Chao Zheng, Jing Yang, Yuxiang Wang, Liming Wang, Yang Wu, Yunjian Zhang

Previous works on word-level attacks widely use word importance ranking (WIR) methods and complex search methods, including greedy search and heuristic algorithms, to find optimal substitutions.

Adversarial Text

Random Orthogonalization for Federated Learning in Massive MIMO Systems

no code implementations18 Oct 2022 Xizixiang Wei, Cong Shen, Jing Yang, H. Vincent Poor

We propose a novel communication design, termed random orthogonalization, for federated learning (FL) in a massive multiple-input and multiple-output (MIMO) wireless system.

Federated Learning

Span-based joint entity and relation extraction augmented with sequence tagging mechanism

no code implementations23 Oct 2022 Bin Ji, Shasha Li, Hao Xu, Jie Yu, Jun Ma, Huijun Liu, Jing Yang

On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE.

Joint Entity and Relation Extraction named-entity-recognition +3

FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection

no code implementations11 Nov 2022 Jing Yang, Jie Shen, Yiming Lin, Yordan Hristov, Maja Pantic

Our model consists of a hybrid network of convolution and transformer blocks to learn per-AU features and to model AU co-occurrences.

Action Unit Detection Face Alignment +2

Determinate Node Selection for Semi-supervised Classification Oriented Graph Convolutional Networks

no code implementations11 Jan 2023 Yao Xiao, Ji Xu, Jing Yang, Shaobo Li

Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data.

Node Classification

ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-Identification

no code implementations11 Feb 2023 Jing Yang, Jianwu Fang, Hongke Xu

With the large-scale and dynamic road environment, the paradigm of supervised vehicle re-identification shows limited scalability because of the heavy reliance on large-scale annotated datasets.

Self-Supervised Learning Unsupervised Vehicle Re-Identification +1

Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction

no code implementations9 Mar 2023 Jing Yang, Bin Ji, Shasha Li, Jun Ma, Long Peng, Jie Yu

Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction.

Relation Relation Extraction

Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs

no code implementations20 Mar 2023 Yuan Cheng, Ruiquan Huang, Jing Yang, Yingbin Liang

In this work, we first provide the first known sample complexity lower bound that holds for any algorithm under low-rank MDPs.

reinforcement-learning Reinforcement Learning (RL) +1

Reward Teaching for Federated Multi-armed Bandits

no code implementations3 May 2023 Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang

Rigorous analyses demonstrate that when facing clients with UCB1, TWL outperforms TAL in terms of the dependencies on sub-optimality gaps thanks to its adaptive design.

Multi-Armed Bandits

Non-stationary Reinforcement Learning under General Function Approximation

no code implementations1 Jun 2023 Songtao Feng, Ming Yin, Ruiquan Huang, Yu-Xiang Wang, Jing Yang, Yingbin Liang

To the best of our knowledge, this is the first dynamic regret analysis in non-stationary MDPs with general function approximation.

reinforcement-learning Reinforcement Learning (RL)

Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints

no code implementations9 Jun 2023 Donghao Li, Ruiquan Huang, Cong Shen, Jing Yang

This paper investigates conservative exploration in reinforcement learning where the performance of the learning agent is guaranteed to be above a certain threshold throughout the learning process.

reinforcement-learning

Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources

no code implementations14 Jun 2023 Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang

Then, a novel HetPEVI algorithm is proposed, which simultaneously considers the sample uncertainties from a finite number of data samples per data source and the source uncertainties due to a finite number of available data sources.

Offline RL reinforcement-learning +1

Differentially Private Wireless Federated Learning Using Orthogonal Sequences

no code implementations14 Jun 2023 Xizixiang Wei, Tianhao Wang, Ruiquan Huang, Cong Shen, Jing Yang, H. Vincent Poor

A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels.

Federated Learning Privacy Preserving

The Age of Synthetic Realities: Challenges and Opportunities

no code implementations9 Jun 2023 João Phillipe Cardenuto, Jing Yang, Rafael Padilha, Renjie Wan, Daniel Moreira, Haoliang Li, Shiqi Wang, Fernanda Andaló, Sébastien Marcel, Anderson Rocha

Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data to construct new narratives or realities, regardless of the intent to deceive.

Misinformation

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations

no code implementations1 Jul 2023 Ruiquan Huang, Yingbin Liang, Jing Yang

The general sequential decision-making problem, which includes Markov decision processes (MDPs) and partially observable MDPs (POMDPs) as special cases, aims at maximizing a cumulative reward by making a sequence of decisions based on a history of observations and actions over time.

Computational Efficiency Decision Making

Tolerating Annotation Displacement in Dense Object Counting via Point Annotation Probability Map

no code implementations29 Jul 2023 Yuehai Chen, Jing Yang, Badong Chen, Hua Gang, Shaoyi Du

To improve the robustness to annotation displacement, we design an effective transport cost function based on GGD.

Object Counting regression

Model-Free Algorithm with Improved Sample Efficiency for Zero-Sum Markov Games

no code implementations17 Aug 2023 Songtao Feng, Ming Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang

In this work, we propose a model-free stage-based Q-learning algorithm and show that it achieves the same sample complexity as the best model-based algorithm, and hence for the first time demonstrate that model-free algorithms can enjoy the same optimality in the $H$ dependence as model-based algorithms.

Multi-agent Reinforcement Learning Q-Learning +1

Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes

no code implementations20 Oct 2023 Ruiquan Huang, Yuan Cheng, Jing Yang, Vincent Tan, Yingbin Liang

To this end, we posit a joint model class for tasks and use the notion of $\eta$-bracketing number to quantify its complexity; this number also serves as a general metric to capture the similarity of tasks and thus determines the benefit of multi-task over single-task RL.

Decision Making Multi-Task Learning +1

A New Approach to Intuitionistic Fuzzy Decision Making Based on Projection Technology and Cosine Similarity Measure

no code implementations20 Nov 2023 Jing Yang, Wei Su

The objective of the presented pa-per is to develop a MADM method and medical diagnosis method under IFS using the projection technology and cosine similarity measure.

Attribute Decision Making +1

Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets

no code implementations19 Nov 2023 Kun Yang, Cong Shen, Jing Yang, Shu-ping Yeh, Jerry Sydir

We observe that the performance of offline RL for the RRM problem depends critically on the behavior policy used for data collection, and further propose a novel offline RL solution that leverages heterogeneous datasets collected by different behavior policies.

Management Offline RL +4

Advancing RAN Slicing with Offline Reinforcement Learning

no code implementations16 Dec 2023 Kun Yang, Shu-ping Yeh, Menglei Zhang, Jerry Sydir, Jing Yang, Cong Shen

Dynamic radio resource management (RRM) in wireless networks presents significant challenges, particularly in the context of Radio Access Network (RAN) slicing.

Management Offline RL +2

Federated Q-Learning: Linear Regret Speedup with Low Communication Cost

no code implementations22 Dec 2023 Zhong Zheng, Fengyu Gao, Lingzhou Xue, Jing Yang

In this paper, we consider federated reinforcement learning for tabular episodic Markov Decision Processes (MDP) where, under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal policy without sharing their raw data.

Q-Learning reinforcement-learning

Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging

no code implementations3 Jan 2024 Jing Yang, Jian Cheng, Cheng Li, Wenxin Fan, Juan Zou, Ruoyou Wu, Shanshan Wang

Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain.

Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generation

no code implementations15 Jan 2024 Zhiwei Lin, Jun Chen, Boshi Tang, Binzhu Sha, Jing Yang, Yaolong Ju, Fan Fan, Shiyin Kang, Zhiyong Wu, Helen Meng

Variational Autoencoders (VAEs) constitute a crucial component of neural symbolic music generation, among which some works have yielded outstanding results and attracted considerable attention.

Music Generation

A Codesign of Scheduling and Parallelization for Large Model Training in Heterogeneous Clusters

no code implementations24 Mar 2024 Chunyu Xue, Weihao Cui, Han Zhao, Quan Chen, Shulai Zhang, Pengyu Yang, Jing Yang, Shaobo Li, Minyi Guo

The exponentially enlarged scheduling space and ever-changing optimal parallelism plan from adaptive parallelism together result in the contradiction between low-overhead and accurate performance data acquisition for efficient cluster scheduling.

Scheduling

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