no code implementations • EACL (WASSA) 2021 • Wazir Ali, Naveed Ali, Yong Dai, Jay Kumar, Saifullah Tumrani, Zenglin Xu
In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers.
no code implementations • RANLP 2021 • Wazir Ali, Zenglin Xu, Jay Kumar
In this paper, we introduce the SiPOS dataset for part-of-speech tagging in the low-resource Sindhi language with quality baselines.
no code implementations • 15 Apr 2024 • Junfan Li, Zenglin Xu, Zheshun Wu, Irwin King
We consider online model selection with decentralized data over $M$ clients, and study a fundamental problem: the necessity of collaboration.
no code implementations • 28 Mar 2024 • Liangjian Wen, Xiasi Wang, Jianzhuang Liu, Zenglin Xu
One can learn this representation by maximizing the mutual information between the representation and the supervised view while eliminating superfluous information.
no code implementations • 10 Mar 2024 • Zhuo Zhang, Jingyuan Zhang, Jintao Huang, Lizhen Qu, Hongzhi Zhang, Zenglin Xu
Extensive experiments on real-world medical data demonstrate the effectiveness of FedPIT in improving federated few-shot performance while preserving privacy and robustness against data heterogeneity.
no code implementations • 1 Mar 2024 • shiyi qi, Liangjian Wen, Yiduo Li, Yuanhang Yang, Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu
To substantiate this claim, we introduce the Cross-variable Decorrelation Aware feature Modeling (CDAM) for Channel-mixing approaches, aiming to refine Channel-mixing by minimizing redundant information between channels while enhancing relevant mutual information.
no code implementations • 27 Feb 2024 • Yuanhang Yang, shiyi qi, Wenchao Gu, Chaozheng Wang, Cuiyun Gao, Zenglin Xu
To address this issue, we present \tool, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models.
no code implementations • 25 Feb 2024 • shiyi qi, Zenglin Xu, Yiduo Li, Liangjian Wen, Qingsong Wen, Qifan Wang, Yuan Qi
Recent advancements in deep learning have led to the development of various models for long-term multivariate time-series forecasting (LMTF), many of which have shown promising results.
no code implementations • 1 Feb 2024 • Maolin Wang, Yu Pan, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao, Wanyu Wang, Yiqi Wang, Zitao Liu, Langming Liu
Our contributions encompass the introduction of a pioneering CDF-based TPP model, the development of a methodology for incorporating past event information into future event prediction, and empirical validation of CuFun's effectiveness through extensive experimentation on synthetic and real-world datasets.
1 code implementation • 17 Jan 2024 • Yu Pan, Ye Yuan, Yichun Yin, Jiaxin Shi, Zenglin Xu, Ming Zhang, Lifeng Shang, Xin Jiang, Qun Liu
The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes.
no code implementations • 1 Jan 2024 • Jinglong Luo, Yehong Zhang, JiaQi Zhang, Xin Mu, Hui Wang, Yue Yu, Zenglin Xu
However, the application of SMPC in Privacy-Preserving Inference (PPI) for large language models, particularly those based on the Transformer architecture, often leads to considerable slowdowns or declines in performance.
no code implementations • 21 Dec 2023 • Zheshun Wu, Zenglin Xu, Dun Zeng, Junfan Li, Jie Liu
To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound.
1 code implementation • 12 Dec 2023 • Dun Zeng, Yong Dai, Pengyu Cheng, Longyue Wang, Tianhao Hu, Wanshun Chen, Nan Du, Zenglin Xu
Our analysis reveals a correlation between the calibration performance of reward models (RMs) and the alignment performance of LLMs.
no code implementations • 17 Nov 2023 • Maolin Wang, Dun Zeng, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao
To address these issues, we propose a novel method, i. e., Federated Latent Embedding Sharing Tensor factorization (FLEST), which is a novel approach using federated tensor factorization for KG completion.
no code implementations • 30 Oct 2023 • Xiangli Yang, Xinglin Pan, Irwin King, Zenglin Xu
To address the GCD without knowing the class number of unlabeled dataset, we propose a co-training-based framework that encourages clustering consistency.
no code implementations • 25 Oct 2023 • Zheshun Wu, Zenglin Xu, Hongfang Yu, Jie Liu
In FEEL, both mobile devices transmitting model parameters over noisy channels and collecting data in diverse environments pose challenges to the generalization of trained models.
no code implementations • 11 Oct 2023 • Zheshun Wu, Zenglin Xu, Dun Zeng, Qifan Wang, Jie Liu
Federated Learning (FL) has surged in prominence due to its capability of collaborative model training without direct data sharing.
no code implementations • 5 Oct 2023 • Xu Luo, Difan Zou, Lianli Gao, Zenglin Xu, Jingkuan Song
Transferring a pretrained model to a downstream task can be as easy as conducting linear probing with target data, that is, training a linear classifier upon frozen features extracted from the pretrained model.
1 code implementation • 4 Oct 2023 • Dun Zeng, Zenglin Xu, Yu Pan, Qifan Wang, Xiaoying Tang
The combined effects of statistical and system heterogeneity can significantly reduce the efficiency of federated optimization.
no code implementations • 4 Oct 2023 • Dun Zeng, Zenglin Xu, Yu Pan, Xu Luo, Qifan Wang, Xiaoying Tang
Central to this process is the technique of unbiased client sampling, which ensures a representative selection of clients.
no code implementations • 5 Jul 2023 • Shiyu Liu, Shaogao Lv, Dun Zeng, Zenglin Xu, Hui Wang, Yue Yu
Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data.
no code implementations • 26 Jun 2023 • Jinglong Luo, Yehong Zhang, JiaQi Zhang, Shuang Qin, Hui Wang, Yue Yu, Zenglin Xu
In contrast to existing studies that protect the data privacy of GPR via homomorphic encryption, differential privacy, or federated learning, our proposed method is more practical and can be used to preserve the data privacy of both the model inputs and outputs for various data-sharing scenarios (e. g., horizontally/vertically-partitioned data).
1 code implementation • 20 Jun 2023 • Siqi Liang, Jintao Huang, Junyuan Hong, Dun Zeng, Jiayu Zhou, Zenglin Xu
Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients.
1 code implementation • 6 Jun 2023 • Bin Hu, Chenyang Zhao, Pu Zhang, ZiHao Zhou, Yuanhang Yang, Zenglin Xu, Bin Liu
In this paper, we explore how to enable intelligent cost-effective interactions between the agent and an LLM.
no code implementations • 5 Jun 2023 • Maolin Wang, Yaoming Zhen, Yu Pan, Yao Zhao, Chenyi Zhuang, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao
THNN is a faithful hypergraph modeling framework through high-order outer product feature message passing and is a natural tensor extension of the adjacency-matrix-based graph neural networks.
1 code implementation • 18 May 2023 • Zhe Li, shiyi qi, Yiduo Li, Zenglin Xu
In this paper, we thoroughly investigate the intrinsic effectiveness of recent approaches and make three key observations: 1) linear mapping is critical to prior long-term time series forecasting efforts; 2) RevIN (reversible normalization) and CI (Channel Independent) play a vital role in improving overall forecasting performance; and 3) linear mapping can effectively capture periodic features in time series and has robustness for different periods across channels when increasing the input horizon.
no code implementations • 20 Mar 2023 • Ying Mo, Hongyin Tang, Jiahao Liu, Qifan Wang, Zenglin Xu, Jingang Wang, Wei Wu, Zhoujun Li
There are three types of NER tasks, including flat, nested and discontinuous entity recognition.
no code implementations • 2 Mar 2023 • Dun Zeng, Xiangjing Hu, Shiyu Liu, Yue Yu, Qifan Wang, Zenglin Xu
Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices.
no code implementations • 21 Feb 2023 • Yifei Zhang, Dun Zeng, Jinglong Luo, Zenglin Xu, Irwin King
Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly benefited human society.
no code implementations • 14 Feb 2023 • Qingzhong Ai, Pengyun Wang, Lirong He, Liangjian Wen, Lujia Pan, Zenglin Xu
Learning with imbalanced data is a challenging problem in deep learning.
1 code implementation • 9 Feb 2023 • Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu
Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) it is important to model the mapping between the input and the prediction sequence.
1 code implementation • 22 Jan 2023 • Maolin Wang, Yu Pan, Zenglin Xu, Xiangli Yang, Guangxi Li, Andrzej Cichocki
Interestingly, although these two types of networks originate from different observations, they are inherently linked through the common multilinearity structure underlying both TNs and NNs, thereby motivating a significant number of intellectual developments regarding combinations of TNs and NNs.
1 code implementation • 21 Jan 2023 • Zhe Li, Zhongwen Rao, Lujia Pan, Pengyun Wang, Zenglin Xu
Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios.
Contrastive Learning Multivariate Time Series Forecasting +2
no code implementations • ICCV 2023 • Fangfei Lin, Bing Bai, Yiwen Guo, Hao Chen, Yazhou Ren, Zenglin Xu
Multi-view hierarchical clustering (MCHC) plays a pivotal role in comprehending the structures within multi-view data, which hinges on the skillful interaction between hierarchical feature learning and comprehensive representation learning across multiple views.
1 code implementation • 20 Dec 2022 • Zhuo Zhang, Yuanhang Yang, Yong Dai, Lizhen Qu, Zenglin Xu
To facilitate the research of PETuning in FL, we also develop a federated tuning framework FedPETuning, which allows practitioners to exploit different PETuning methods under the FL training paradigm conveniently.
no code implementations • 19 Dec 2022 • Zi Gong, Yinpeng Guo, Pingyi Zhou, Cuiyun Gao, Yasheng Wang, Zenglin Xu
On the other hand, there are few studies exploring the effects of multi-programming-lingual (MultiPL) pre-training for the code completion, especially the impact on low-resource programming languages.
2 code implementations • 30 Oct 2022 • Jing Xu, Xu Luo, Xinglin Pan, Wenjie Pei, Yanan Li, Zenglin Xu
In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid -- the mean of all class centroids in the task.
1 code implementation • 11 Oct 2022 • Yuanhang Yang, shiyi qi, Chuanyi Liu, Qifan Wang, Cuiyun Gao, Zenglin Xu
Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI).
no code implementations • 11 Oct 2022 • Terry Yue Zhuo, Yaqing Liao, Yuecheng Lei, Lizhen Qu, Gerard de Melo, Xiaojun Chang, Yazhou Ren, Zenglin Xu
We introduce ViLPAct, a novel vision-language benchmark for human activity planning.
no code implementations • IEEE 38th International Conference on Data Engineering (ICDE) 2022 • Ge Fan, Chaoyun Zhang, Junyang Chen, Baopu Li, Zenglin Xu, Yingjie Li, Luyu Peng, Zhiguo Gong
Moreover, we deploy the proposed method in real-world applications and conduct online A/B tests in a look-alike system.
1 code implementation • 16 Jun 2022 • Xu Luo, Jing Xu, Zenglin Xu
When facing novel few-shot tasks in the test-time datasets, this transformation can greatly improve the generalization ability of learned image representations, while being agnostic to the choice of training algorithms and datasets.
no code implementations • 16 Jun 2022 • Langzhang Liang, Zenglin Xu, Zixing Song, Irwin King, Jieping Ye
In detail, by studying the long-tailed distribution of node degrees in the graph, we propose a novel normalization method for GNNs, which is termed ResNorm (\textbf{Res}haping the long-tailed distribution into a normal-like distribution via \textbf{norm}alization).
1 code implementation • 28 May 2022 • Yu Pan, Zeyong Su, Ao Liu, Jingquan Wang, Nannan Li, Zenglin Xu
To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs.
no code implementations • 26 May 2022 • Dun Zeng, Shiyu Liu, Siqi Liang, Zonghang Li, Hui Wang, Irwin King, Zenglin Xu
However, privacy information could be leaked from uploaded gradients and be exposed to malicious attackers or an honest-but-curious server.
no code implementations • 5 May 2022 • Fangfei Lin, Bing Bai, Kun Bai, Yazhou Ren, Peng Zhao, Zenglin Xu
Then, we embed the representations into a hyperbolic space and optimize the hyperbolic embeddings via a continuous relaxation of hierarchical clustering loss.
1 code implementation • 12 Mar 2022 • Linyang Li, Yong Dai, Duyu Tang, Xipeng Qiu, Zenglin Xu, Shuming Shi
We present a Chinese BERT model dubbed MarkBERT that uses word information in this work.
Chinese Named Entity Recognition named-entity-recognition +7
no code implementations • 17 Feb 2022 • Jingquan Wang, Jing Xu, Yu Pan, Zenglin Xu
Few-shot learning aims to classify unseen classes with only a limited number of labeled data.
1 code implementation • 14 Feb 2022 • Zi Gong, Cuiyun Gao, Yasheng Wang, Wenchao Gu, Yun Peng, Zenglin Xu
We further show that how the proposed SCRIPT captures the structural relative dependencies.
1 code implementation • 3 Feb 2022 • Zonghang Li, Yihong He, Hongfang Yu, Jiawen Kang, Xiaoping Li, Zenglin Xu, Dusit Niyato
In this paper, we propose FedGS, which is a hierarchical cloud-edge-end FL framework for 5G empowered industries, to improve industrial FL performance on non-i. i. d.
no code implementations • 31 Jan 2022 • Shenglai Zeng, Zonghang Li, Hongfang Yu, Yihong He, Zenglin Xu, Dusit Niyato, Han Yu
In this paper, we propose a data heterogeneity-robust FL approach, FedGSP, to address this challenge by leveraging on a novel concept of dynamic Sequential-to-Parallel (STP) collaborative training.
no code implementations • 14 Dec 2021 • Jing Xu, Xinglin Pan, Xu Luo, Wenjie Pei, Zenglin Xu
To alleviate this problem, we present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge.
1 code implementation • 13 Dec 2021 • Lili Pan, Mingming Meng, Yazhou Ren, Yali Zheng, Zenglin Xu
To answer this question, this paper proposes a new SPL method: easy and underrepresented examples first, for learning DDMs.
no code implementations • 9 Nov 2021 • Chaozheng Wang, Shuzheng Gao, Cuiyun Gao, Pengyun Wang, Wenjie Pei, Lujia Pan, Zenglin Xu
Real-world data usually present long-tailed distributions.
no code implementations • 18 Oct 2021 • Langzhang Liang, Cuiyun Gao, Shiyi Chen, Shishi Duan, Yu Pan, Junjin Zheng, Lei Wang, Zenglin Xu
Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification.
1 code implementation • 24 Jul 2021 • Dun Zeng, Siqi Liang, Xiangjing Hu, Hui Wang, Zenglin Xu
Federated learning (FL) is a machine learning field in which researchers try to facilitate model learning process among multiparty without violating privacy protection regulations.
1 code implementation • 20 Jul 2021 • Xu Luo, Yuxuan Chen, Liangjian Wen, Lili Pan, Zenglin Xu
The goal of few-shot classification is to classify new categories with few labeled examples within each class.
1 code implementation • NeurIPS 2021 • Qingzhong Ai, Lirong He, Shiyu Liu, Zenglin Xu
To address this issue, we propose Bayesian Pseudocoresets Exemplar VAE (ByPE-VAE), a new variant of VAE with a prior based on Bayesian pseudocoreset.
no code implementations • 20 Jul 2021 • Qingzhong Ai, Shiyu Liu, Lirong He, Zenglin Xu
In practice, we notice that the kernel used in SVGD-based methods has a decisive effect on the empirical performance.
1 code implementation • NeurIPS 2021 • Xu Luo, Longhui Wei, Liangjian Wen, Jinrong Yang, Lingxi Xie, Zenglin Xu, Qi Tian
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL).
1 code implementation • 16 Jun 2021 • Xianghong Fang, Haoli Bai, Jian Li, Zenglin Xu, Michael Lyu, Irwin King
We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse.
no code implementations • 10 May 2021 • Xinglin Pan, Jing Xu, Yu Pan, Liangjian Wen, WenXiang Lin, Kun Bai, Zenglin Xu
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification.
no code implementations • 9 May 2021 • Yong Dai, Jian Liu, Jian Zhang, Hongguang Fu, Zenglin Xu
The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.
1 code implementation • 11 Apr 2021 • Yu Pan, Maolin Wang, Zenglin Xu
Tensor Decomposition Networks (TDNs) prevail for their inherent compact architectures.
1 code implementation • 8 Apr 2021 • Juncheng Lv, Zhao Kang, Xiao Lu, Zenglin Xu
To tackle these problems, we use pairwise similarity to weigh the reconstruction loss to capture local structure information, while a similarity is learned by the self-expression layer.
no code implementations • 10 Mar 2021 • Ping Guo, Kaizhu Huang, Zenglin Xu
In this work, we generalize the reaction-diffusion equation in statistical physics, Schr\"odinger equation in quantum mechanics, Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research.
no code implementations • 5 Mar 2021 • Lili Pan, Peijun Tang, Zhiyong Chen, Zenglin Xu
Disentanglement is defined as the problem of learninga representation that can separate the distinct, informativefactors of variations of data.
no code implementations • 28 Feb 2021 • Xiangli Yang, Zixing Song, Irwin King, Zenglin Xu
Deep semi-supervised learning is a fast-growing field with a range of practical applications.
1 code implementation • 26 Feb 2021 • Zixing Song, Xiangli Yang, Zenglin Xu, Irwin King
An important class of SSL methods is to naturally represent data as graphs such that the label information of unlabelled samples can be inferred from the graphs, which corresponds to graph-based semi-supervised learning (GSSL) methods.
1 code implementation • 25 Jan 2021 • Jing Xu, Tszhang Guo, Yong Xu, Zenglin Xu, Kun Bai
Deep Convolutional Neural Networks (DCNNs) and their variants have been widely used in large scale face recognition(FR) recently.
14 code implementations • 3 Jan 2021 • Jing Xu, Yu Pan, Xinglin Pan, Steven Hoi, Zhang Yi, Zenglin Xu
The ResNet and its variants have achieved remarkable successes in various computer vision tasks.
Ranked #3 on Medical Image Classification on NCT-CRC-HE-100K
no code implementations • 1 Jan 2021 • Xinglin Pan, Jing Xu, Yu Pan, WenXiang Lin, Liangjian Wen, Zenglin Xu
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks, e. g., image classification.
no code implementations • 1 Jan 2021 • Xu Luo, Yuxuan Chen, Liangjian Wen, Lili Pan, Zenglin Xu
Few-shot learning aims to recognize new classes with few annotated instances within each category.
no code implementations • 30 Dec 2020 • Wazir Ali, Jay Kumar, Zenglin Xu, Congjian Luo, Junyu Lu, Junming Shao, Rajesh Kumar, Yazhou Ren
The word segmentation is a fundamental and inevitable prerequisite for many languages.
no code implementations • 10 Oct 2020 • Jinmian Ye, Guangxi Li, Di Chen, Haiqin Yang, Shandian Zhe, Zenglin Xu
Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e. g., image classification, natural language processing, etc.
no code implementations • 22 Sep 2020 • Nannan Li, Yu Pan, Yaran Chen, Zixiang Ding, Dongbin Zhao, Zenglin Xu
Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region.
no code implementations • 31 Aug 2020 • Zhao Kang, Chong Peng, Qiang Cheng, Xinwang Liu, Xi Peng, Zenglin Xu, Ling Tian
Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus they might not achieve the optimal performance.
1 code implementation • 26 Jul 2020 • Jie Xu, Yazhou Ren, Guofeng Li, Lili Pan, Ce Zhu, Zenglin Xu
Firstly, the embedded representations of multiple views are learned individually by deep autoencoders.
1 code implementation • 14 Jul 2020 • Lun Yiu Nie, Cuiyun Gao, Zhicong Zhong, Wai Lam, Yang Liu, Zenglin Xu
In this paper, we propose a novel Contextualized code representation learning strategy for commit message Generation (CoreGen).
no code implementations • 11 Jul 2020 • Zhao Kang, Xiao Lu, Jian Liang, Kun Bai, Zenglin Xu
In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning.
no code implementations • 10 Jun 2020 • Yong Dai, Jian Liu, Xiancong Ren, Zenglin Xu
Existing algorithms of MS-UDA either only exploit the shared features, i. e., the domain-invariant information, or based on some weak assumption in NLP, e. g., smoothness assumption.
Multi-Source Unsupervised Domain Adaptation Sentiment Analysis +2
no code implementations • 12 May 2020 • Yitian Li, Ruini Xue, Mengmeng Zhu, Jing Xu, Zenglin Xu
Many complex network structures are proposed recently and many of them concentrate on multi-branch features to achieve high performance.
1 code implementation • ICLR 2020 • Liangjian Wen, Yiji Zhou, Lirong He, Mingyuan Zhou, Zenglin Xu
To this end, we propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions.
no code implementations • LREC 2020 • Wazir Ali, Junyu Lu, Zenglin Xu
We introduce the SiNER: a named entity recognition (NER) dataset for low-resourced Sindhi language with quality baselines.
no code implementations • 21 Apr 2020 • Xianghong Fang, Haoli Bai, Zenglin Xu, Michael Lyu, Irwin King
Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse.
no code implementations • ECCV 2020 • Lili Pan, Shijie Ai, Yazhou Ren, Zenglin Xu
Deep discriminative models (e. g. deep regression forests, deep neural decision forests) have achieved remarkable success recently to solve problems such as facial age estimation and head pose estimation.
no code implementations • 3 Dec 2019 • Zhao Kang, Xiao Lu, Yiwei Lu, Chong Peng, Zenglin Xu
Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications.
no code implementations • 3 Dec 2019 • Juncheng Lv, Zhao Kang, Boyu Wang, Luping Ji, Zenglin Xu
Multi-view clustering is an important approach to analyze multi-view data in an unsupervised way.
no code implementations • 28 Nov 2019 • Wazir Ali, Jay Kumar, Junyu Lu, Zenglin Xu
Our intrinsic evaluation results demonstrate the high quality of our generated Sindhi word embeddings using SG, CBoW, and GloVe as compare to SdfastText word representations.
2 code implementations • 21 Nov 2019 • Zhao Kang, Wangtao Zhou, Zhitong Zhao, Junming Shao, Meng Han, Zenglin Xu
A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years.
no code implementations • 20 Nov 2019 • Lirong He, Ziyi Guo, Kai-Zhu Huang, Zenglin Xu
In a worst-case scenario, MPM tries to minimize an upper bound of misclassification probabilities, considering the global information (i. e., mean and covariance information of each class).
no code implementations • 15 Nov 2019 • Shufei Zhang, Kai-Zhu Huang, Zenglin Xu
We propose to exploit an energy function to describe the stability and prove that reducing such energy guarantees the robustness against adversarial examples.
1 code implementation • 16 Sep 2019 • Zhao Kang, Guoxin Shi, Shudong Huang, Wenyu Chen, Xiaorong Pu, Joey Tianyi Zhou, Zenglin Xu
Most existing methods don't pay attention to the quality of the graphs and perform graph learning and spectral clustering separately.
1 code implementation • 13 Sep 2019 • Zhao Kang, Zipeng Guo, Shudong Huang, Siying Wang, Wenyu Chen, Yuanzhang Su, Zenglin Xu
Most existing multi-view clustering methods explore the heterogeneous information in the space where the data points lie.
1 code implementation • ACL 2019 • Junyu Lu, Chenbin Zhang, Zeying Xie, Guang Ling, Tom Chao Zhou, Zenglin Xu
Response selection plays an important role in fully automated dialogue systems.
no code implementations • 17 Jun 2019 • Liangjian Wen, Xuanyang Zhang, Haoli Bai, Zenglin Xu
Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications.
no code implementations • 21 May 2019 • Zhao Kang, Honghui Xu, Boyu Wang, Hongyuan Zhu, Zenglin Xu
A key step of graph-based approach is the similarity graph construction.
1 code implementation • CVPR 2019 • Jian Liang, Yuren Cao, Chenbin Zhang, Shiyu Chang, Kun Bai, Zenglin Xu
Authentication is a task aiming to confirm the truth between data instances and personal identities.
no code implementations • ICLR 2019 • Xuanyang Zhang, Hao liu, Zhanxing Zhu, Zenglin Xu
Deep neural networks have achieved outstanding performance in many real-world applications with the expense of huge computational resources.
no code implementations • 14 Mar 2019 • Zhao Kang, Liangjian Wen, Wenyu Chen, Zenglin Xu
By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other.
1 code implementation • 11 Mar 2019 • Zhao Kang, Yiwei Lu, Yuanzhang Su, Changsheng Li, Zenglin Xu
Data similarity is a key concept in many data-driven applications.
1 code implementation • Neurocomputing 2019 • Yazhou Ren, Kangrong Hu, Xinyi Dai, Lili Pan, Steven C. H. Hoi, Zenglin Xu
Deep embedded clustering (DEC) is one of the state-of-the-art deep clustering methods.
no code implementations • 30 Dec 2018 • Xianghong Fang, Haoli Bai, Ziyi Guo, Bin Shen, Steven Hoi, Zenglin Xu
In this paper, we propose a new unsupervised domain adaptation method named Domain-Adversarial Residual-Transfer (DART) learning of Deep Neural Networks to tackle cross-domain image classification tasks.
no code implementations • 17 Dec 2018 • Lili Pan, Shen Cheng, Jian Liu, Yazhou Ren, Zenglin Xu
We study the problem of multimodal generative modelling of images based on generative adversarial networks (GANs).
2 code implementations • 17 Dec 2018 • Zhao Kang, Haiqi Pan, Steven C. H. Hoi, Zenglin Xu
The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption, 2) improved graph construction by exploiting clean data recovered by robust PCA.
1 code implementation • 11 Dec 2018 • Yazhou Ren, Ni Wang, Mingxia Li, Zenglin Xu
Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications.
Ranked #1 on Image Clustering on LetterA-J
1 code implementation • NIPS Workshop CDNNRIA 2018 • Yu Pan, Jing Xu, Maolin Wang, Jinmian Ye, Fei Wang, Kun Bai, Zenglin Xu
Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling.
1 code implementation • 24 Aug 2018 • Yazhou Ren, Xiaofan Que, Dezhong Yao, Zenglin Xu
Despite the success of traditional MTC models, they are either easy to stuck into local optima, or sensitive to outliers and noisy data.
no code implementations • 20 Jun 2018 • Zhao Kang, Xiao Lu, Jin-Feng Yi, Zenglin Xu
There are two possible reasons for the failure: (i) most existing MKL methods assume that the optimal kernel is a linear combination of base kernels, which may not hold true; and (ii) some kernel weights are inappropriately assigned due to noises and carelessly designed algorithms.
1 code implementation • 21 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.
no code implementations • 13 Jan 2018 • Linnan Wang, Jinmian Ye, Yiyang Zhao, Wei Wu, Ang Li, Shuaiwen Leon Song, Zenglin Xu, Tim Kraska
Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance.
no code implementations • 15 Dec 2017 • Guangxi Li, Jinmian Ye, Haiqin Yang, Di Chen, Shuicheng Yan, Zenglin Xu
Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification.
no code implementations • CVPR 2018 • Jinmian Ye, Linnan Wang, Guangxi Li, Di Chen, Shandian Zhe, Xinqi Chu, Zenglin Xu
On three challenging tasks, including Action Recognition in Videos, Image Captioning and Image Generation, BT-RNN outperforms TT-RNN and the standard RNN in terms of both prediction accuracy and convergence rate.
no code implementations • 16 Nov 2017 • Dan Ma, Bin Liu, Zhao Kang, Jiayu Zhou, Jianke Zhu, Zenglin Xu
Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications.
1 code implementation • 12 Nov 2017 • Zhao Kang, Chong Peng, Qiang Cheng, Zenglin Xu
Second, the discrete solution may deviate from the spectral solution since k-means method is well-known as sensitive to the initialization of cluster centers.
no code implementations • 24 May 2017 • Hao Liu, Haoli Bai, Lirong He, Zenglin Xu
Inheriting these advantages of stochastic neural sequential models, we propose a structured and stochastic sequential neural network, which models both the long-term dependencies via recurrent neural networks and the uncertainty in the segmentation and labels via discrete random variables.
no code implementations • 11 Nov 2016 • Guangxi Li, Zenglin Xu, Linnan Wang, Jinmian Ye, Irwin King, Michael Lyu
Probabilistic Temporal Tensor Factorization (PTTF) is an effective algorithm to model the temporal tensor data.
no code implementations • 3 Nov 2016 • Bin Liu, Zenglin Xu, Yingming Li
Another assumption of these methods is that a predefined rank should be known.
no code implementations • NeurIPS 2016 • Shandian Zhe, Kai Zhang, Pengyuan Wang, Kuang-Chih Lee, Zenglin Xu, Yuan Qi, Zoubin Ghahramani
Tensor factorization is a powerful tool to analyse multi-way data.
no code implementations • NeurIPS 2013 • Shouyuan Chen, Michael R. Lyu, Irwin King, Zenglin Xu
For the noisy cases, we also prove error bounds for a constrained convex program for recovering the tensors.
no code implementations • 26 Apr 2013 • Shandian Zhe, Zenglin Xu, Yuan Qi
To unify these two tasks, we present a new sparse Bayesian approach for joint association study and disease diagnosis.
no code implementations • 15 Mar 2012 • Kaizhu Huang, Rong Jin, Zenglin Xu, Cheng-Lin Liu
Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints.
no code implementations • NeurIPS 2009 • Zhirong Yang, Irwin King, Zenglin Xu, Erkki Oja
Based on this finding, we present a parameterized subset of similarity functions for choosing the best tail-heaviness for HSSNE; (2) we present a fixed-point optimization algorithm that can be applied to all heavy-tailed functions and does not require the user to set any parameters; and (3) we present two empirical studies, one for unsupervised visualization showing that our optimization algorithm runs as fast and as good as the best known t-SNE implementation and the other for semi-supervised visualization showing quantitative superiority using the homogeneity measure as well as qualitative advantage in cluster separation over t-SNE.
no code implementations • NeurIPS 2009 • Zenglin Xu, Rong Jin, Jianke Zhu, Irwin King, Michael Lyu, Zhirong Yang
In this framework, SVM and TSVM can be regarded as a learning machine without regularization and one with full regularization from the unlabeled data, respectively.
no code implementations • NeurIPS 2008 • Zenglin Xu, Rong Jin, Irwin King, Michael Lyu
We consider the problem of multiple kernel learning (MKL), which can be formulated as a convex-concave problem.
no code implementations • NeurIPS 2007 • Zenglin Xu, Rong Jin, Jianke Zhu, Irwin King, Michael Lyu
We consider the problem of Support Vector Machine transduction, which involves a combinatorial problem with exponential computational complexity in the number of unlabeled examples.