Search Results for author: Jiancheng Lv

Found 60 papers, 24 papers with code

Federated cINN Clustering for Accurate Clustered Federated Learning

no code implementations4 Sep 2023 Yuhao Zhou, Minjia Shi, Yuxin Tian, Yuanxi Li, Qing Ye, Jiancheng Lv

However, a significant challenge arises when coordinating FL with crowd intelligence which diverse client groups possess disparate objectives due to data heterogeneity or distinct tasks.

Clustering Federated Learning +1

GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model

no code implementations9 May 2023 Caiyang Yu, Xianggen Liu, Wentao Feng, Chenwei Tang, Jiancheng Lv

Neural Architecture Search (NAS) has emerged as one of the effective methods to design the optimal neural network architecture automatically.

Neural Architecture Search

Deep Lifelong Cross-modal Hashing

no code implementations26 Apr 2023 Liming Xu, Hanqi Li, Bochuan Zheng, Weisheng Li, Jiancheng Lv

To this end, we, in this paper, propose a novel deep lifelong cross-modal hashing to achieve lifelong hashing retrieval instead of re-training hash function repeatedly when new data arrive.

Cross-Modal Retrieval Retrieval +2

Differentiable Genetic Programming for High-dimensional Symbolic Regression

no code implementations18 Apr 2023 Peng Zeng, Xiaotian Song, Andrew Lensen, Yuwei Ou, Yanan sun, Mengjie Zhang, Jiancheng Lv

With these designs, the proposed DGP method can efficiently search for the GP trees with higher performance, thus being capable of dealing with high-dimensional SR. To demonstrate the effectiveness of DGP, we conducted various experiments against the state of the arts based on both GP and deep neural networks.

Interpretable Machine Learning regression +2

Dual Contrastive Prediction for Incomplete Multi-view Representation Learning

1 code implementation IEEE Transactions on Pattern Analysis and Machine Intelligence 2023 Yijie Lin, Yuanbiao Gou, Xiaotian Liu, Jinfeng Bai, Jiancheng Lv, Xi Peng

In this article, we propose a unified framework to solve the following two challenging problems in incomplete multi-view representation learning: i) how to learn a consistent representation unifying different views, and ii) how to recover the missing views.

Action Recognition Contrastive Learning +3

Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence

no code implementations27 Feb 2023 Yuhao Zhou, Mingjia Shi, Yuanxi Li, Qing Ye, Yanan sun, Jiancheng Lv

Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning.

Federated Learning Privacy Preserving

Comprehensive and Delicate: An Efficient Transformer for Image Restoration

1 code implementation CVPR 2023 Haiyu Zhao, Yuanbiao Gou, Boyun Li, Dezhong Peng, Jiancheng Lv, Xi Peng

Vision Transformers have shown promising performance in image restoration, which usually conduct window- or channel-based attention to avoid intensive computations.

Image Restoration Superpixels

Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective

no code implementations CVPR 2023 Yuanbiao Gou, Peng Hu, Jiancheng Lv, Hongyuan Zhu, Xi Peng

Existing studies have empirically observed that the resolution of the low-frequency region is easier to enhance than that of the high-frequency one.

Image Super-Resolution

Sample-Level Multi-View Graph Clustering

no code implementations CVPR 2023 Yuze Tan, Yixi Liu, Shudong Huang, Wentao Feng, Jiancheng Lv

Multi-view clustering have hitherto been studied due to their effectiveness in dealing with heterogeneous data.

Clustering Graph Clustering

Differentiable Search of Accurate and Robust Architectures

no code implementations28 Dec 2022 Yuwei Ou, Xiangning Xie, Shangce Gao, Yanan sun, Kay Chen Tan, Jiancheng Lv

Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense.

Personalized Federated Learning with Hidden Information on Personalized Prior

no code implementations19 Nov 2022 Mingjia Shi, Yuhao Zhou, Qing Ye, Jiancheng Lv

Federated learning (FL for simplification) is a distributed machine learning technique that utilizes global servers and collaborative clients to achieve privacy-preserving global model training without direct data sharing.

 Ranked #1 on Image Classification on Fashion-MNIST (Accuracy metric)

Classification Image Classification +2

Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition

1 code implementation7 Nov 2022 Youcheng Huang, Wenqiang Lei, Jie Fu, Jiancheng Lv

Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition.

named-entity-recognition Named Entity Recognition +1

Partial Differential Equations Meet Deep Neural Networks: A Survey

no code implementations27 Oct 2022 Shudong Huang, Wentao Feng, Chenwei Tang, Jiancheng Lv

Many problems in science and engineering can be represented by a set of partial differential equations (PDEs) through mathematical modeling.

Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric

no code implementations CVPR 2023 Pengxin Zeng, Yunfan Li, Peng Hu, Dezhong Peng, Jiancheng Lv, Xi Peng

Fair clustering aims to divide data into distinct clusters while preventing sensitive attributes (\textit{e. g.}, gender, race, RNA sequencing technique) from dominating the clustering.

Clustering Fairness

Draft, Command, and Edit: Controllable Text Editing in E-Commerce

no code implementations11 Aug 2022 Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Qian Qu, Jiancheng Lv

To address this challenge, we explore a new draft-command-edit manner in description generation, leading to the proposed new task-controllable text editing in E-commerce.

Data Augmentation

Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy

no code implementations7 Apr 2022 Wenqiang Lei, Yao Zhang, Feifan Song, Hongru Liang, Jiaxin Mao, Jiancheng Lv, Zhenglu Yang, Tat-Seng Chua

To this end, we contribute to advance the study of the proactive dialogue policy to a more natural and challenging setting, i. e., interacting dynamically with users.

DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg

no code implementations6 Apr 2022 Yuhao Zhou, Minjia Shi, Yuxin Tian, Qing Ye, Jiancheng Lv

Federated learning (FL) is identified as a crucial enabler for large-scale distributed machine learning (ML) without the need for local raw dataset sharing, substantially reducing privacy concerns and alleviating the isolated data problem.

Federated Learning

Multi-Scale Adaptive Network for Single Image Denoising

1 code implementation8 Mar 2022 Yuanbiao Gou, Peng Hu, Jiancheng Lv, Joey Tianyi Zhou, Xi Peng

AFuB devotes to adaptively sampling and transferring the features from one scale to another scale, which fuses the multi-scale features with varying characteristics from coarse to fine.

Image Denoising

Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning

no code implementations5 Mar 2022 Yi Gao, Chenwei Tang, Jiancheng Lv

Generalized Zero-Shot Learning (GZSL) aims to recognize both seen and unseen classes by training only the seen classes, in which the instances of unseen classes tend to be biased towards the seen class.

Contrastive Learning Generalized Zero-Shot Learning

All-in-One Image Restoration for Unknown Corruption

1 code implementation CVPR 2022 Boyun Li, Xiao Liu, Peng Hu, Zhongqin Wu, Jiancheng Lv, Xi Peng

In this paper, we study a challenging problem in image restoration, namely, how to develop an all-in-one method that could recover images from a variety of unknown corruption types and levels.

Image Restoration

Face Deblurring Based on Separable Normalization and Adaptive Denormalization

no code implementations18 Dec 2021 Xian Zhang, Hao Zhang, Jiancheng Lv, Xiaojie Li

Face deblurring aims to restore a clear face image from a blurred input image with more explicit structure and facial details.

Deblurring Face Parsing +1

Adversarial Retriever-Ranker for dense text retrieval

1 code implementation ICLR 2022 Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan, Weizhu Chen

To address these challenges, we present Adversarial Retriever-Ranker (AR2), which consists of a dual-encoder retriever plus a cross-encoder ranker.

Natural Questions Retrieval +2

POS-Constrained Parallel Decoding for Non-autoregressive Generation

1 code implementation ACL 2021 Kexin Yang, Wenqiang Lei, Dayiheng Liu, Weizhen Qi, Jiancheng Lv

However, in this work, we experimentally reveal that this assumption does not always hold for the text generation tasks like text summarization and story ending generation.

Knowledge Distillation POS +2

Unsupervised Neural Rendering for Image Hazing

no code implementations14 Jul 2021 Boyun Li, Yijie Lin, Xiao Liu, Peng Hu, Jiancheng Lv, Xi Peng

To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i. e., unpaired real hazy images.

Image Dehazing Neural Rendering

TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance

1 code implementation ACL 2021 Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua

In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions.

Question Answering

Poolingformer: Long Document Modeling with Pooling Attention

no code implementations10 May 2021 Hang Zhang, Yeyun Gong, Yelong Shen, Weisheng Li, Jiancheng Lv, Nan Duan, Weizhu Chen

We first evaluate Poolingformer on two long sequence QA tasks: the monolingual NQ and the multilingual TyDi QA.

Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search

no code implementations3 May 2021 Jindi Lv, Qing Ye, Yanan sun, Juan Zhao, Jiancheng Lv

In this paper, we propose a novel approach, Heart-Darts, to efficiently classify the ECG signals by automatically designing the CNN model with the differentiable architecture search (i. e., Darts, a cell-based neural architecture search method).

Arrhythmia Detection Classification +3

Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System

no code implementations23 Apr 2021 Cheng Luo, Dayiheng Liu, Chanjuan Li, Li Lu, Jiancheng Lv

The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation.

Dialogue Generation

LANA: Towards Personalized Deep Knowledge Tracing Through Distinguishable Interactive Sequences

1 code implementation21 Apr 2021 Yuhao Zhou, Xihua Li, Yunbo Cao, Xuemin Zhao, Qing Ye, Jiancheng Lv

With pivot module reconstructed the decoder for individual students and leveled learning specialized encoders for groups, personalized DKT was achieved.

Knowledge Tracing

COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction

1 code implementation CVPR 2021 Yijie Lin, Yuanbiao Gou, Zitao Liu, Boyun Li, Jiancheng Lv, Xi Peng

In this paper, we study two challenging problems in incomplete multi-view clustering analysis, namely, i) how to learn an informative and consistent representation among different views without the help of labels and ii) how to recover the missing views from data.

Clustering Contrastive Learning +2

Dynamic Normalization

no code implementations15 Jan 2021 Chuan Liu, Yi Gao, Jiancheng Lv

It allows the network to use a higher learning rate and speed up training.

Communication-Efficient Federated Learning with Compensated Overlap-FedAvg

1 code implementation12 Dec 2020 Yuhao Zhou, Ye Qing, Jiancheng Lv

Petabytes of data are generated each day by emerging Internet of Things (IoT), but only few of them can be finally collected and used for Machine Learning (ML) purposes due to the apprehension of data & privacy leakage, which seriously retarding ML's growth.

Data Compression Federated Learning

Partially View-aligned Clustering

no code implementations NeurIPS 2020 Zhenyu Huang, Peng Hu, Joey Tianyi Zhou, Jiancheng Lv, Xi Peng

To solve this practical and challenging problem, we propose a novel multi-view clustering method termed partially view-aligned clustering (PVC).


Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space

1 code implementation EMNLP 2020 Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Jiancheng Lv, Nan Duan, Ming Zhou

In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answering natural language inference tasks.

Data Augmentation Machine Reading Comprehension +6

HPSGD: Hierarchical Parallel SGD With Stale Gradients Featuring

1 code implementation6 Sep 2020 Yuhao Zhou, Qing Ye, Hailun Zhang, Jiancheng Lv

While distributed training significantly speeds up the training process of the deep neural network (DNN), the utilization of the cluster is relatively low due to the time-consuming data synchronizing between workers.

DBS: Dynamic Batch Size For Distributed Deep Neural Network Training

1 code implementation23 Jul 2020 Qing Ye, Yuhao Zhou, Mingjia Shi, Yanan sun, Jiancheng Lv

Specifically, the performance of each worker is evaluatedfirst based on the fact in the previous epoch, and then the batch size and datasetpartition are dynamically adjusted in consideration of the current performanceof the worker, thereby improving the utilization of the cluster.

RikiNet: Reading Wikipedia Pages for Natural Question Answering

no code implementations ACL 2020 Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Nan Duan

The representations are then fed into the predictor to obtain the span of the short answer, the paragraph of the long answer, and the answer type in a cascaded manner.

Natural Language Understanding Natural Questions +1

Let's be Humorous: Knowledge Enhanced Humor Generation

no code implementations ACL 2020 Hang Zhang, Dayiheng Liu, Jiancheng Lv, Cheng Luo

To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model.

Learning Event-Based Motion Deblurring

no code implementations CVPR 2020 Zhe Jiang, Yu Zhang, Dongqing Zou, Jimmy Ren, Jiancheng Lv, Yebin Liu

Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process.

Ranked #20 on Image Deblurring on GoPro (using extra training data)

Deblurring Image Deblurring

Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation

1 code implementation EMNLP 2020 Dayiheng Liu, Yeyun Gong, Jie Fu, Wei Liu, Yu Yan, Bo Shao, Daxin Jiang, Jiancheng Lv, Nan Duan

Furthermore, we propose a simple and effective method to mine the keyphrases of interest in the news article and build a first large-scale keyphrase-aware news headline corpus, which contains over 180K aligned triples of $<$news article, headline, keyphrase$>$.

Headline Generation

Generating Chinese Poetry from Images via Concrete and Abstract Information

no code implementations24 Mar 2020 Yusen Liu, Dayiheng Liu, Jiancheng Lv, Yongsheng Sang

We proposed an infilling-based Chinese poetry generation model which can infill the Concrete keywords into each line of poems in an explicit way, and an abstract information embedding to integrate the Abstract information into generated poems.

ArcText: A Unified Text Approach to Describing Convolutional Neural Network Architectures

no code implementations16 Feb 2020 Yanan Sun, Ziyao Ren, Gary G. Yen, Bing Xue, Mengjie Zhang, Jiancheng Lv

Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs.

Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting

no code implementations5 Feb 2020 Xian Zhang, Xin Wang, Bin Kong, Youbing Yin, Qi Song, Siwei Lyu, Jiancheng Lv, Canghong Shi, Xiaojie Li

We firstly represent only face regions using the latent variable as the domain knowledge and combine it with the non-face parts textures to generate high-quality face images with plausible contents.

Facial Inpainting

Deep Poetry: A Chinese Classical Poetry Generation System

no code implementations19 Nov 2019 Yusen Liu, Dayiheng Liu, Jiancheng Lv

For the user's convenience, we deploy the system at the WeChat applet platform, users can use the system on the mobile device whenever and wherever possible.

Deep Density-aware Count Regressor

1 code implementation9 Aug 2019 Zhuojun Chen, Junhao Cheng, Yuchen Yuan, Dongping Liao, Yizhou Li, Jiancheng Lv

We seek to improve crowd counting as we perceive limits of currently prevalent density map estimation approach on both prediction accuracy and time efficiency.

Crowd Counting

Deep Learning-Based Automatic Downbeat Tracking: A Brief Review

1 code implementation10 Jun 2019 Bijue Jia, Jiancheng Lv, Dayiheng Liu

Thereinto, downbeat tracking has been a fundamental and continuous problem in Music Information Retrieval (MIR) area.

Feature Engineering Information Retrieval +3

Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning

1 code implementation29 May 2019 Dayiheng Liu, Jie Fu, Yidan Zhang, Chris Pal, Jiancheng Lv

We propose a new framework that utilizes the gradients to revise the sentence in a continuous space during inference to achieve text style transfer.

Disentanglement Style Transfer +2

TIGS: An Inference Algorithm for Text Infilling with Gradient Search

1 code implementation ACL 2019 Dayiheng Liu, Jie Fu, PengFei Liu, Jiancheng Lv

Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios.

Text Infilling

mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation

2 code implementations24 May 2019 Dayiheng Liu, Xu Yang, Feng He, YuanYuan Chen, Jiancheng Lv

It has been previously observed that training Variational Recurrent Autoencoders (VRAE) for text generation suffers from serious uninformative latent variables problem.

Language Modelling Text Generation

Learning Discriminative Representation with Signed Laplacian Restricted Boltzmann Machine

no code implementations28 Aug 2018 Dongdong Chen, Jiancheng Lv, Mike E. Davies

We investigate the potential of a restricted Boltzmann Machine (RBM) for discriminative representation learning.

Representation Learning

XAI Beyond Classification: Interpretable Neural Clustering

no code implementations22 Aug 2018 Xi Peng, Yunnan Li, Ivor W. Tsang, Hongyuan Zhu, Jiancheng Lv, Joey Tianyi Zhou

The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning.

Classification Clustering +3

A Multi-Modal Chinese Poetry Generation Model

1 code implementation26 Jun 2018 Dayiheng Liu, Quan Guo, Wubo Li, Jiancheng Lv

Given a picture, the first line, the title and the other lines of the poem are successively generated in three stages.

BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation

no code implementations21 Jun 2018 Dayiheng Liu, Jie Fu, Qian Qu, Jiancheng Lv

Incorporating prior knowledge like lexical constraints into the model's output to generate meaningful and coherent sentences has many applications in dialogue system, machine translation, image captioning, etc.

Image Captioning Machine Translation +1

Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets

no code implementations29 Mar 2017 Junyu Luo, Yong Xu, Chenwei Tang, Jiancheng Lv

The inverse mapping of GANs'(Generative Adversarial Nets) generator has a great potential value. Hence, some works have been developed to construct the inverse function of generator by directly learning or adversarial learning. While the results are encouraging, the problem is highly challenging and the existing ways of training inverse models of GANs have many disadvantages, such as hard to train or poor performance. Due to these reasons, we propose a new approach based on using inverse generator ($IG$) model as encoder and pre-trained generator ($G$) as decoder of an AutoEncoder network to train the $IG$ model.

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