no code implementations • ICML 2020 • Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao
For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.
no code implementations • IWSLT (EMNLP) 2018 • Yuguang Wang, Liangliang Shi, Linyu Wei, Weifeng Zhu, Jinkun Chen, Zhichao Wang, Shixue Wen, Wei Chen, Yanfeng Wang, Jia Jia
Our final average result on speech translation is 31. 02 BLEU.
1 code implementation • EMNLP 2021 • Hao Zhou, Minlie Huang, Yong liu, Wei Chen, Xiaoyan Zhu
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
1 code implementation • COLING 2022 • Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu
Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.
1 code implementation • ECCV 2020 • Baojie Fan, Wei Chen, Yang Cong, Jiandong Tian
Due to the complex underwater environment, underwater imaging often encounters some problems such as blur, scale variation, color shift, and texture distortion.
no code implementations • 31 Jan 2023 • Shi Feng, Nuoya Xiong, Wei Chen
This paper studies the CCB problem without the graph structure on binary general causal models and BGLMs.
1 code implementation • 28 Jan 2023 • Haozhe Feng, Tianyu Pang, Chao Du, Wei Chen, Shuicheng Yan, Min Lin
BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server.
no code implementations • 25 Jan 2023 • Yingchaojie Feng, Xingbo Wang, Bo Pan, Kam Kwai Wong, Yi Ren, Shi Liu, Zihan Yan, Yuxin Ma, Huamin Qu, Wei Chen
Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries.
no code implementations • 11 Jan 2023 • Yongqiang Mao, Kaiqiang Chen, Liangjin Zhao, Wei Chen, Deke Tang, Wenjie Liu, Zhirui Wang, Wenhui Diao, Xian Sun, Kun fu
Our Building3D is rooted in the SFFDE network for building elevation prediction, synchronized with a building extraction network for building masks, and then sequentially performs point cloud reconstruction, surface reconstruction (or CityGML model reconstruction).
no code implementations • 11 Jan 2023 • Zhu Liang, Matthew R. Carbone, Wei Chen, Fanchen Meng, Eli Stavitski, Deyu Lu, Mark S. Hybertsen, Xiaohui Qu
A new semi-supervised machine learning method for the discovery of structure-spectrum relationships is developed and demonstrated using the specific example of interpreting X-ray absorption near-edge structure (XANES) spectra.
2 code implementations • 2 Jan 2023 • Steven H. Wang, Antoine Scardigli, Leonard Tang, Wei Chen, Dimitry Levkin, Anya Chen, Spencer Ball, Thomas Woodside, Oliver Zhang, Dan Hendrycks
Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets.
no code implementations • 21 Dec 2022 • Rusheng Pan, Zhiyong Wang, Yating Wei, Han Gao, Gongchang Ou, Caleb Chen Cao, Jingli Xu, Tong Xu, Wei Chen
A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators.
no code implementations • 9 Dec 2022 • Wei Chen, Xi Jia, Zhongqun Zhang, Hyung Jin Chang, Linlin Shen, Jinming Duan, Ales Leonardis
The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task.
no code implementations • 29 Nov 2022 • Wei Chen, Weixiao Wan, Shiyue Wang, Peng Sun, Bo Ai
This paper presents a novel method for massive MIMO CSI feedback via a one-sided deep learning framework.
1 code implementation • 29 Nov 2022 • Xi Jia, Joseph Bartlett, Wei Chen, Siyang Song, Tianyang Zhang, Xinxing Cheng, Wenqi Lu, Zhaowen Qiu, Jinming Duan
Specifically, instead of our Fourier-Net learning to output a full-resolution displacement field in the spatial domain, we learn its low-dimensional representation in a band-limited Fourier domain.
1 code implementation • 27 Nov 2022 • Wei Chen, Chen Li, Dan Chen, Xin Luo
Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee of quality.
no code implementations • 21 Nov 2022 • Wei Chen, Yansheng Li, Bo Dang, Yongjun Zhang
This paper presents a new paradigm for Extra-large image semantic Segmentation, called ElegantSeg, that capably processes holistic extra-large image semantic segmentation (ELISS).
1 code implementation • 15 Nov 2022 • Hengrui Zhang, Wei Wayne Chen, James M. Rondinelli, Wei Chen
To mitigate the bias, we develop an entropy-targeted active learning (ET-AL) framework, which guides the acquisition of new data to improve the diversity of underrepresented crystal systems.
no code implementations • 8 Nov 2022 • Dan Wang, Wei Chen, Li Qiu
They can also model the controllers of the agents which may be different for each agent or uniform for all the agents.
no code implementations • 7 Nov 2022 • Andrey Ignatov, Radu Timofte, Cheng-Ming Chiang, Hsien-Kai Kuo, Yu-Syuan Xu, Man-Yu Lee, Allen Lu, Chia-Ming Cheng, Chih-Cheng Chen, Jia-Ying Yong, Hong-Han Shuai, Wen-Huang Cheng, Zhuang Jia, Tianyu Xu, Yijian Zhang, Long Bao, Heng Sun, Diankai Zhang, Si Gao, Shaoli Liu, Biao Wu, Xiaofeng Zhang, Chengjian Zheng, Kaidi Lu, Ning Wang, Xiao Sun, HaoDong Wu, Xuncheng Liu, Weizhan Zhang, Caixia Yan, Haipeng Du, Qinghua Zheng, Qi Wang, Wangdu Chen, Ran Duan, Mengdi Sun, Dan Zhu, Guannan Chen, Hojin Cho, Steve Kim, Shijie Yue, Chenghua Li, Zhengyang Zhuge, Wei Chen, Wenxu Wang, Yufeng Zhou, Xiaochen Cai, Hengxing Cai, Kele Xu, Li Liu, Zehua Cheng, Wenyi Lian, Wenjing Lian
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
no code implementations • 4 Nov 2022 • Suraj Yerramilli, Akshay Iyer, Wei Chen, Daniel W. Apley
However, this plug-in approach will not account for uncertainty in estimation of the LVs, which can be significant especially with limited training data.
no code implementations • 27 Oct 2022 • Rudong An, Wei zhang, Hao Zeng, Wei Chen, Zhigang Deng, Yu Ding
Then, AU feature maps and their corresponding AU masks are multiplied to generate AU masked features focusing on local facial region.
no code implementations • 25 Oct 2022 • Zhipeng Hu, Wei zhang, Lincheng Li, Yu Ding, Wei Chen, Zhigang Deng, Xin Yu
We find that AUs and facial expressions are highly associated, and existing facial expression datasets often contain a large number of identities.
2 code implementations • 13 Oct 2022 • Jian-Wei Zhang, Yifan Sun, Yi Yang, Wei Chen
With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head.
no code implementations • 4 Oct 2022 • Zixuan Zhang, Yuning Jiang, Yuanming Shi, Ye Shi, Wei Chen
This paper develops an optimal EV charging/discharging control strategy for different EV users under dynamic environments to maximize EV users' benefits.
1 code implementation • 14 Sep 2022 • Chen Wu, Ruqing Zhang, Jiafeng Guo, Wei Chen, Yixing Fan, Maarten de Rijke, Xueqi Cheng
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
no code implementations • 9 Sep 2022 • Yanfang Mo, Wei Chen, Keyou You, Li Qiu
We propose and examine two optimal $(0, 1)$-matrix completion problems with majorization ordered objectives.
no code implementations • 3 Sep 2022 • Shangfei Zheng, Weiqing Wang, Jianfeng Qu, Hongzhi Yin, Wei Chen, Lei Zhao
Multi-modal knowledge graphs (MKGs) include not only the relation triplets, but also related multi-modal auxiliary data (i. e., texts and images), which enhance the diversity of knowledge.
1 code implementation • 3 Sep 2022 • Yufeng Zhang, Weiqing Wang, Hongzhi Yin, Pengpeng Zhao, Wei Chen, Lei Zhao
A more challenging scenario is that emerging KGs consist of only unseen entities, called as disconnected emerging KGs (DEKGs).
no code implementations • 31 Aug 2022 • Xutong Liu, Jinhang Zuo, Siwei Wang, Carlee Joe-Wong, John C. S. Lui, Wei Chen
Under this new condition, we propose a BCUCB-T algorithm with variance-aware confidence intervals and conduct regret analysis which reduces the $O(K)$ factor to $O(\log K)$ or $O(\log^2 K)$ in the regret bound, significantly improving the regret bounds for the above applications.
1 code implementation • COLING 2022 • Wei Chen, Jinglong Du, Zhao Zhang, Fuzhen Zhuang, Zhongshi He
Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments (sentiment classification).
no code implementations • 21 Aug 2022 • Bohan Wang, Yushun Zhang, Huishuai Zhang, Qi Meng, Zhi-Ming Ma, Tie-Yan Liu, Wei Chen
In particular, the existing analysis of Adam cannot clearly demonstrate the advantage of Adam over SGD.
no code implementations • 15 Aug 2022 • Yuxue Ren, Baowei Jiang, Wei Chen, Na lei, Xianfeng David Gu
We present a novel, effective method for global point cloud registration problems by geometric topology.
1 code implementation • 21 Jul 2022 • Yuzhen Zhang, Wentong Wang, Weizhi Guo, Pei Lv, Mingliang Xu, Wei Chen, Dinesh Manocha
We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space.
no code implementations • 11 Jul 2022 • Hengrui Zhang, Wei Wayne Chen, Akshay Iyer, Daniel W. Apley, Wei Chen
Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods.
no code implementations • 27 Jun 2022 • Xiaodong Yang, Huishuai Zhang, Wei Chen, Tie-Yan Liu
By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data.
no code implementations • 16 Jun 2022 • Nuoya Xiong, Wei Chen
The combinatorial pure exploration of causal bandits is the following online learning task: given a causal graph with unknown causal inference distributions, in each round we choose a subset of variables to intervene or do no intervention, and observe the random outcomes of all random variables, with the goal that using as few rounds as possible, we can output an intervention that gives the best (or almost best) expected outcome on the reward variable $Y$ with probability at least $1-\delta$, where $\delta$ is a given confidence level.
1 code implementation • 4 Jun 2022 • Shi Feng, Wei Chen
For the special case of linear models with hidden variables, we apply causal inference techniques such as the do-calculus to convert the original model into a Markovian model, and then show that our BGLM-OFU algorithm and another algorithm based on the linear regression both solve such linear models with hidden variables.
1 code implementation • 25 May 2022 • Jiawei Huang, Li Zhao, Tao Qin, Wei Chen, Nan Jiang, Tie-Yan Liu
We propose a new learning framework that captures the tiered structure of many real-world user-interaction applications, where the users can be divided into two groups based on their different tolerance on exploration risks and should be treated separately.
1 code implementation • 8 May 2022 • Wei Chen, Shuzhe Li, Chao Huang, Yanwei Yu, Yongguo Jiang, Junyu Dong
In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL.
1 code implementation • 8 May 2022 • Wei Chen, Cheng Zhong, Jiajie Peng, Zhongyu Wei
Diagnosis-oriented dialogue system queries the patient's health condition and makes predictions about possible diseases through continuous interaction with the patient.
no code implementations • 7 May 2022 • Zijian Li, Ruichu Cai, Jiawei Chen, Yuguan Yan, Wei Chen, Keli Zhang, Junjian Ye
Based on this inspiration, we investigate the domain-invariant unweighted sparse associative structures and the domain-variant strengths of the structures.
1 code implementation • ACL 2022 • Wei Chen, Yeyun Gong, Song Wang, Bolun Yao, Weizhen Qi, Zhongyu Wei, Xiaowu Hu, Bartuer Zhou, Yi Mao, Weizhu Chen, Biao Cheng, Nan Duan
Dialog response generation in open domain is an important research topic where the main challenge is to generate relevant and diverse responses.
no code implementations • 19 Apr 2022 • Wei Chen, Jie Zhao, Wan-Lei Zhao, Song-Yuan Wu
In this paper, a single-stage monocular 3D object detection model is proposed.
1 code implementation • 19 Apr 2022 • Wei Chen, Zhiwei Li, Hongyi Fang, Qianyuan Yao, Cheng Zhong, Jianye Hao, Qi Zhang, Xuanjing Huang, Jiajie Peng, Zhongyu Wei
In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.
1 code implementation • 13 Apr 2022 • Peiyan Hu, Qi Meng, Bingguang Chen, Shiqi Gong, Yue Wang, Wei Chen, Rongchan Zhu, Zhi-Ming Ma, Tie-Yan Liu
Stochastic partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics.
1 code implementation • 7 Apr 2022 • Zheng Chen, Ziwei Yang, Lingwei Zhu, Wei Chen, Toshiyo Tamura, Naoaki Ono, MD Altaf-Ul-Amin, Shigehiko Kanaya, Ming Huang
This paper proposes a novel framework for automatically capturing the time-frequency nature of electroencephalogram (EEG) signals of human sleep based on the authoritative sleep medicine guidance.
1 code implementation • CVPR 2022 • Shian Du, Yihong Luo, Wei Chen, Jian Xu, Delu Zeng
In this paper, a temporal optimization is proposed by optimizing the evolutionary time for forward propagation of the neural ODE training.
no code implementations • 21 Feb 2022 • Doksoo Lee, Yu-Chin Chan, Wei Wayne Chen, LiWei Wang, Anton van Beek, Wei Chen
Distinctly, we seek a solution to a commonplace yet frequently overlooked scenario at early stages of data-driven design of metamaterials: when a massive (~O(10^4 )) shape-only library has been prepared with no properties evaluated.
1 code implementation • 21 Feb 2022 • Wei Wayne Chen, Doksoo Lee, Oluwaseyi Balogun, Wei Chen
To address this issue, we propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF), which contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design.
no code implementations • 16 Feb 2022 • Yihan Du, Wei Chen
In this paper, we propose a novel Branching Reinforcement Learning (Branching RL) model, and investigate both Regret Minimization (RM) and Reward-Free Exploration (RFE) metrics for this model.
no code implementations • 16 Jan 2022 • Di Zhao, Wei Chen, Li Qiu
In this paper, we investigate the feedback stability of multiple-input multiple-output linear time-invariant systems with combined gain and phase information.
1 code implementation • 13 Jan 2022 • Ruichu Cai, Fengzhu Wu, Zijian Li, Jie Qiao, Wei Chen, Yuexing Hao, Hao Gu
By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method.
no code implementations • 5 Jan 2022 • Esin Darici Haritaoglu, Nicholas Rasmussen, Daniel C. H. Tan, Jennifer Ranjani J., Jaclyn Xiao, Gunvant Chaudhari, Akanksha Rajput, Praveen Govindan, Christian Canham, Wei Chen, Minami Yamaura, Laura Gomezjurado, Aaron Broukhim, Amil Khanzada, Mert Pilanci
The Covid-19 pandemic has been one of the most devastating events in recent history, claiming the lives of more than 5 million people worldwide.
no code implementations • 29 Dec 2021 • Andreas Pfadler, Rong Zhu, Wei Chen, Botong Huang, Tianjing Zeng, Bolin Ding, Jingren Zhou
Based on the high level architecture, we then describe a concrete implementation of Baihe for PostgreSQL and present example use cases for learned query optimizers.
1 code implementation • 15 Dec 2021 • Wei Wayne Chen, Doksoo Lee, Wei Chen
Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization.
no code implementations • 7 Dec 2021 • Rong Zhu, Tianjing Zeng, Andreas Pfadler, Wei Chen, Bolin Ding, Jingren Zhou
Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS.
1 code implementation • 1 Dec 2021 • Yu-Chin Chan, Daicong Da, LiWei Wang, Wei Chen
We propose to inherit the advantages of both through a data-driven framework for multiclass functionally graded structures that mixes several families, i. e., classes, of microstructure topologies to create spatially-varying designs with guaranteed feasibility.
1 code implementation • NeurIPS 2021 • Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu
To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.
no code implementations • 18 Nov 2021 • Wei Chen, Yunjin Wu, Ruichu Cai, Yueguo Chen, Zhifeng Hao
Specifically, for the former, we provide a Causality-related Chinese Restaurant Process to cluster samples based on the similarity of the causal structure; for the latter, we introduce a variational-inference-based approach to learn the causal structures.
no code implementations • NeurIPS 2021 • Fang Kong, Yueran Yang, Wei Chen, Shuai Li
These are the first theoretical results for TS to solve CMAB with a common approximation oracle and break the misconception that TS cannot work with approximation oracles.
1 code implementation • 1 Nov 2021 • Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
We are the first to unveil an important population property of the perturbations of these attacks: they are almost \textbf{linearly separable} when assigned with the target labels of the corresponding samples, which hence can work as \emph{shortcuts} for the learning objective.
no code implementations • 29 Oct 2021 • Yihan Du, Wei Chen, Yuko Kuroki, Longbo Huang
In this paper, we formulate a Collaborative Pure Exploration in Kernel Bandit problem (CoPE-KB), which provides a novel model for multi-agent multi-task decision making under limited communication and general reward functions, and is applicable to many online learning tasks, e. g., recommendation systems and network scheduling.
1 code implementation • 26 Oct 2021 • Weitao Du, He Zhang, Yuanqi Du, Qi Meng, Wei Chen, Bin Shao, Tie-Yan Liu
In this paper, we propose a framework to construct SE(3) equivariant graph neural networks that can approximate the geometric quantities efficiently.
no code implementations • NeurIPS 2021 • Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu
We prove that with constraint to guarantee low empirical risk, the optimal noise covariance is the square root of the expected gradient covariance if both the prior and the posterior are jointly optimized.
no code implementations • 19 Oct 2021 • Atul Sharma, Wei Chen, Joshua Zhao, Qiang Qiu, Somali Chaterji, Saurabh Bagchi
The attack uses the intuition that simply by changing the sign of the gradient updates that the optimizer is computing, for a set of malicious clients, a model can be diverted from the optima to increase the test error rate.
no code implementations • 8 Oct 2021 • Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
The momentum acceleration technique is widely adopted in many optimization algorithms.
2 code implementations • ICLR 2022 • Chongchong Li, Yue Wang, Wei Chen, YuTing Liu, Zhi-Ming Ma, Tie-Yan Liu
Then we proposed a two-model-based learning method to control the prediction error and the gradient error.
no code implementations • 29 Sep 2021 • Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu
In contextual bandit, one major challenge is to develop theoretically solid and empirically efficient algorithms for general function classes.
1 code implementation • ICLR 2022 • Zichen Miao, Ze Wang, Wei Chen, Qiang Qiu
In this paper, we first enforce a low-rank filter subspace by decomposing convolutional filters within each network layer over a small set of filter atoms.
1 code implementation • ACL 2022 • Wei Chen, Yeyun Gong, Can Xu, Huang Hu, Bolun Yao, Zhongyu Wei, Zhihao Fan, Xiaowu Hu, Bartuer Zhou, Biao Cheng, Daxin Jiang, Nan Duan
We study the problem of coarse-grained response selection in retrieval-based dialogue systems.
no code implementations • 13 Sep 2021 • Zhijie Zhang, Wei Chen, Xiaoming Sun, Jialin Zhang
We study the online influence maximization (OIM) problem in social networks, where the learner repeatedly chooses seed nodes to generate cascades, observes the cascade feedback, and gradually learns the best seeds that generate the largest cascade in multiple rounds.
no code implementations • EMNLP 2021 • Liqiang Xiao, Jun Ma2, Xin Luna Dong, Pascual Martinez-Gomez, Nasser Zalmout, Wei Chen, Tong Zhao, Hao He, Yaohui Jin
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers.
no code implementations • 3 Sep 2021 • Chao Chen, Wei Chen, Di Zhao, Sei Zhen Khong, Li Qiu
It is, thus, different from the recently appeared nonlinear system phase which adopts the complexification of real-valued signals using the Hilbert transform.
no code implementations • 6 Aug 2021 • Johannes Knittel, Steffen Koch, Tan Tang, Wei Chen, Yingcai Wu, Shixia Liu, Thomas Ertl
In contrast to previous work, our system also works with non-geolocated posts and avoids extensive preprocessing such as detecting events.
no code implementations • 29 Jun 2021 • Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu
However, it is in general unknown how to deriveefficient and effective EE trade-off methods for non-linearcomplex tasks, suchas contextual bandit with deep neural network as the reward function.
9 code implementations • NeurIPS 2021 • Xiaobo Liang, Lijun Wu, Juntao Li, Yue Wang, Qi Meng, Tao Qin, Wei Chen, Min Zhang, Tie-Yan Liu
Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
Ranked #4 on
Machine Translation
on WMT2014 English-French
no code implementations • 26 Jun 2021 • LiWei Wang, Suraj Yerramilli, Akshay Iyer, Daniel Apley, Ping Zhu, Wei Chen
In addition, an interpretable latent space is obtained to draw insights into the effect of categorical factors, such as those associated with building blocks of architectures and element choices in metamaterial and materials design.
no code implementations • 23 Jun 2021 • Xin Luo, Wei Chen, Yusong Tan, Chen Li, Yulin He, Xiaogang Jia
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data.
1 code implementation • 17 Jun 2021 • Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence.
1 code implementation • 13 Jun 2021 • Marija Vella, BoWen Zhang, Wei Chen, João F. C. Mota
Such methods, however, cannot guarantee that the input measurements are satisfied in the recovered image, since the learned parameters by the network are applied to every test image.
1 code implementation • ICLR 2022 • Sang-gil Lee, Heeseung Kim, Chaehun Shin, Xu Tan, Chang Liu, Qi Meng, Tao Qin, Wei Chen, Sungroh Yoon, Tie-Yan Liu
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
no code implementations • 11 Jun 2021 • LiWei Wang, Anton van Beek, Daicong Da, Yu-Chin Chan, Ping Zhu, Wei Chen
After integrating LVGP with the density-based TO, an efficient data-driven cellular composite optimization process is developed to enable concurrent exploration of microstructure concepts and the associated volume fractions for natural frequency optimization.
no code implementations • 9 Jun 2021 • Xutong Liu, Jinhang Zuo, Xiaowei Chen, Wei Chen, John C. S. Lui
For the online learning setting, neither the network structure nor the node weights are known initially.
no code implementations • 8 Jun 2021 • Shiqi Gong, Qi Meng, Yue Wang, Lijun Wu, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
In this paper, to reduce the reliance on the numerical solver, we propose to enhance the supervised signal in the training of NODE.
1 code implementation • 7 Jun 2021 • Jian-Wei Zhang, Wei Chen, K. Ina Ly, Xubin Zhang, Fan Yan, Justin Jordan, Gordon Harris, Scott Plotkin, Pengyi Hao, Wenli Cai
In this study, we propose deep interactive networks (DINs) to address the above limitations.
no code implementations • 7 Jun 2021 • Zhijie Zhang, Wei Chen, Xiaoming Sun, Jialin Zhang
Our IMS algorithms enhance the learning-and-then-optimization approach by allowing a constant approximation ratio even when the diffusion parameters are hard to learn, and we do not need any assumption related to the network structure or diffusion parameters.
1 code implementation • 7 Jun 2021 • Amin Heyrani Nobari, Wei Chen, Faez Ahmed
Engineering design tasks often require synthesizing new designs that meet desired performance requirements.
1 code implementation • NAACL 2021 • Haoran Wu, Wei Chen, Shuang Xu, Bo Xu
Specifically, we first structure the sequence of EMR into a hierarchical graph network and then obtain the causal relationship between multi-granularity features and diagnosis results through counterfactual intervention on the graph.
no code implementations • 1 Jun 2021 • Min Fu, Yong Zhou, Yuanming Shi, Wei Chen, Rui Zhang
Over-the-air computation (AirComp) seamlessly integrates communication and computation by exploiting the waveform superposition property of multiple-access channels.
1 code implementation • 1 Jun 2021 • Jian-Wei Zhang, Lei Lv, Yawei Luo, Hao-Zhe Feng, Yi Yang, Wei Chen
The hierarchical features help the model highlight the decision boundary and focus on hard pixels, and the structural information learned from base classes is treated as the prior knowledge for novel classes.
no code implementations • 31 May 2021 • Ziming Liu, Bohan Wang, Qi Meng, Wei Chen, Max Tegmark, Tie-Yan Liu
Energy conservation is a basic physics principle, the breakdown of which often implies new physics.
1 code implementation • CVPR 2022 • Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu
Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled rejection metrics, which could provably distinguish wrongly classified inputs from correctly classified ones.
no code implementations • 25 May 2021 • Xi Jia, Alexander Thorley, Wei Chen, Huaqi Qiu, Linlin Shen, Iain B Styles, Hyung Jin Chang, Ales Leonardis, Antonio de Marvao, Declan P. O'Regan, Daniel Rueckert, Jinming Duan
We then propose two neural layers (i. e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i. e. generalized denoising layer).
no code implementations • NeurIPS 2021 • Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu
We prove that with constraint to guarantee low empirical risk, the optimal noise covariance is the square root of the expected gradient covariance if both the prior and the posterior are jointly optimized.
1 code implementation • Findings (ACL) 2021 • Chujie Zheng, Yong liu, Wei Chen, Yongcai Leng, Minlie Huang
However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling.
no code implementations • 12 May 2021 • Faez Ahmed, Yaxin Cui, Yan Fu, Wei Chen
By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges.
no code implementations • 11 May 2021 • Wenzhi Fang, Yuning Jiang, Yuanming Shi, Yong Zhou, Wei Chen, Khaled B. Letaief
Over-the-air computation (AirComp) is a disruptive technique for fast wireless data aggregation in Internet of Things (IoT) networks via exploiting the waveform superposition property of multiple-access channels.
no code implementations • 10 May 2021 • Jianqi Chen, Jieqiang Wei, Wei Chen, Henrik Sandberg, Karl H. Johansson, Jie Chen
Undetectable attacks are an important class of malicious attacks threatening the security of cyber-physical systems, which can modify a system's state but leave the system output measurements unaffected, and hence cannot be detected from the output.
no code implementations • 8 May 2021 • Wei Chen, Dan Wang, Sei Zhen Khong, Li Qiu
In this paper, we define the phase response for a class of multi-input multi-output (MIMO) linear time-invariant (LTI) systems whose frequency responses are (semi-)sectorial at all frequencies.
no code implementations • 8 May 2021 • Siwei Wang, Wei Chen
In this paper, we study the pure exploration bandit model on general distribution functions, which means that the reward function of each arm depends on the whole distribution, not only its mean.
no code implementations • 11 Apr 2021 • Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy.
no code implementations • 8 Apr 2021 • Zhichao Wang, Wenwen Yang, Pan Zhou, Wei Chen
Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR).
no code implementations • 31 Mar 2021 • Lintao Li, Longwei Yang, Xin Guo, Yuanming Shi, Haiming Wang, Wei Chen, Khaled B. Letaief
Federated learning (FL) is a collaborative machine learning paradigm, which enables deep learning model training over a large volume of decentralized data residing in mobile devices without accessing clients' private data.
no code implementations • 26 Mar 2021 • Wei Chen, Kun Zhang, Ruichu Cai, Biwei Huang, Joseph Ramsey, Zhifeng Hao, Clark Glymour
The first step of our method uses the FCI procedure, which allows confounders and is able to produce asymptotically correct results.
1 code implementation • CVPR 2021 • Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains.
no code implementations • 12 Mar 2021 • Matheus S. M. de Sousa, Manfred Sigrist, Wei Chen
Even without the magnetization, an out-of-plane polarized chiral edge spin current is produced, resembling that in the quantum spin Hall effect.
Mesoscale and Nanoscale Physics
no code implementations • 12 Mar 2021 • Wei Chen
Signals with single peak and symmetry property are very common in various fields, such as probability density function of normal distribution.
2 code implementations • CVPR 2021 • Wei Chen, Xi Jia, Hyung Jin Chang, Jinming Duan, Linlin Shen, Ales Leonardis
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image.
Ranked #3 on
6D Pose Estimation using RGBD
on REAL275
no code implementations • 11 Mar 2021 • Theodoros Georgiou, Sebastian Schmitt, Thomas Bäck, Nan Pu, Wei Chen, Michael Lew
The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated.
no code implementations • 11 Mar 2021 • Theodoros Georgiou, Sebastian Schmitt, Thomas Bäck, Wei Chen, Michael Lew
In this work we propose a weight soft-regularization method based on the Oblique manifold.
no code implementations • 10 Mar 2021 • Wei Chen
And in such a way, the mode number also can be determined during the separation procedure.
1 code implementation • 10 Mar 2021 • Amin Heyrani Nobari, Wei Chen, Faez Ahmed
This work laid the foundation for data-driven inverse design problems where we consider range constraints and there are sparse regions in the condition space.
no code implementations • 4 Mar 2021 • Wei Chen, Jingya Cui
Let $M$ be the Doob maximal operator on a filtered measure space and let $v$ be an $A_p$ weight with $1<p<+\infty$.
Probability 60G46
no code implementations • 4 Mar 2021 • Jia-Xing Zhang, Lu Yang, Shuang Liang, Wei Chen, Qiang-Hua Wang
We study the possibility to realize Majorana zero mode that's robust and may be easily manipulated for braiding in quantum computing in the ground state of the Kitaev model in this work.
Strongly Correlated Electrons
2 code implementations • ICLR 2021 • Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism.
no code implementations • NeurIPS 2021 • Yihan Du, Yuko Kuroki, Wei Chen
For the FC setting, we propose novel algorithms with optimal sample complexity for a broad family of instances and establish a matching lower bound to demonstrate the optimality (within a logarithmic factor).
no code implementations • 3 Feb 2021 • Xiaogang Jia, Wei Chen, Zhengfa Liang, Mingfei Wu, Yusong Tan, Libo Huang
This is because different cost volumes play a crucial role in balancing speed and accuracy.
no code implementations • 28 Jan 2021 • Kun Luo, Hao Geng, Li Sheng, Wei Chen, D. Y. Xing
Unlike AB interferometer of 3D topological insulator(TI), we find that there are different AB oscillation frequencies for a given direction of magnetic field in 3D HOTI.
Mesoscale and Nanoscale Physics
no code implementations • 27 Jan 2021 • Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
no code implementations • 25 Jan 2021 • Min Fu, Yong Zhou, Yuanming Shi, Ting Wang, Wei Chen
Over-the-air computation (AirComp) provides a promising way to support ultrafast aggregation of distributed data.
Optimize the trajectory of UAV which plays a BS in communication system
no code implementations • 14 Jan 2021 • Zhong Yang, Wei Chen, Yayun He, Weiyao Ke, Longgang Pang, Xin-Nian Wang
Diffusion wake is an unambiguous part of the jet-induced medium response in high-energy heavy-ion collisions that leads to a depletion of soft hadrons in the opposite direction of the jet propagation.
High Energy Physics - Phenomenology
no code implementations • 8 Jan 2021 • Mingyang Yi, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
However, it has been pointed out that the usual definitions of sharpness, which consider either the maxima or the integral of loss over a $\delta$ ball of parameters around minima, cannot give consistent measurement for scale invariant neural networks, e. g., networks with batch normalization layer.
no code implementations • 7 Jan 2021 • Wei Chen, Arun Ramamurthy
We demonstrate FFD-GAN's performance using a wing shape design example.
no code implementations • 1 Jan 2021 • Huishuai Zhang, Da Yu, Wei Chen, Tie-Yan Liu
More importantly, we propose a new design ``STAM aggregation" that can guarantee to STAbilize the forward/backward process of Multi-branch networks irrespective of the number of branches.
1 code implementation • LREC 2022 • Wenhao Zhu, ShuJian Huang, Tong Pu, Pingxuan Huang, Xu Zhang, Jian Yu, Wei Chen, Yanfeng Wang, Jiajun Chen
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios.
1 code implementation • 24 Dec 2020 • Min Zhao, Xiuheng Wang, Jie Chen, Wei Chen
Spectral unmixing is a widely used technique in hyperspectral image processing and analysis.
no code implementations • 22 Dec 2020 • Ruichu Cai, Jiawei Chen, Zijian Li, Wei Chen, Keli Zhang, Junjian Ye, Zhuozhang Li, Xiaoyan Yang, Zhenjie Zhang
To reduce the difficulty in the discovery of causal structure, we relax it to the sparse associative structure and propose a novel sparse associative structure alignment model for domain adaptation.
no code implementations • 19 Dec 2020 • Xinwei Sun, Botong Wu, Wei Chen
To learn such an invariance for deepfake detection, our InTeLe introduces an auto-encoder framework with different decoders for pristine and fake images, which are further appended with a shallow classifier in order to separate out the obvious artifact-effect.
1 code implementation • 11 Dec 2020 • Bohan Wang, Qi Meng, Wei Chen, Tie-Yan Liu
Except GD, adaptive algorithms such as AdaGrad, RMSProp and Adam are popular owing to their rapid training process.
no code implementations • 7 Dec 2020 • Lixin Sun, Jonathan Vandermause, Simon Batzner, Yu Xie, David Clark, Wei Chen, Boris Kozinsky
Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics.
no code implementations • 6 Dec 2020 • Prithu Banerjee, Wei Chen, Laks V. S. Lakshmanan
Competitive IM focuses on the propagation of competing items in the network.
no code implementations • 30 Nov 2020 • Chao Chen, Di Zhao, Wei Chen, Sei Zhen Khong, Li Qiu
A nonlinear small phase theorem is then established for feedback stability analysis of semi-sectorial systems.
3 code implementations • 21 Nov 2020 • Hao-Zhe Feng, Kezhi Kong, Minghao Chen, Tianye Zhang, Minfeng Zhu, Wei Chen
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results.
1 code implementation • 19 Nov 2020 • Hao-Zhe Feng, Zhaoyang You, Minghao Chen, Tianye Zhang, Minfeng Zhu, Fei Wu, Chao Wu, Wei Chen
(2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains.
Knowledge Distillation
Multi-Source Unsupervised Domain Adaptation
+2
no code implementations • 17 Nov 2020 • Guan-Jie Fan-Yuan, Wei Chen, Feng-Yu Lu, Zhen-Qiang Yin, Shuang Wang, Guang-Can Guo, Zheng-Fu Han
Our framework focuses on realistic characters of optical devices and system structures.
Quantum Physics Optics
no code implementations • NeurIPS 2020 • Shuai Li, Fang Kong, Kejie Tang, Qizhi Li, Wei Chen
Based on the linear structure in node activations, we incorporate ideas from linear bandits and design an algorithm LT-LinUCB that is consistent with the observed feedback.
no code implementations • 10 Nov 2020 • Zhibin Wang, Jiahang Qiu, Yong Zhou, Yuanming Shi, Liqun Fu, Wei Chen, Khaled B. Lataief
To optimize the learning performance, we formulate an optimization problem that jointly optimizes the device selection, the aggregation beamformer at the base station (BS), and the phase shifts at the IRS to maximize the number of devices participating in the model aggregation of each communication round under certain mean-squared-error (MSE) requirements.
no code implementations • 9 Nov 2020 • Xiao Gong, Xi Chen, Wei Chen
Video surveillance is gaining increasing popularity to assist in railway intrusion detection in recent years.
no code implementations • 4 Nov 2020 • Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu
To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.
1 code implementation • NeurIPS 2021 • Chang Liu, Xinwei Sun, Jindong Wang, Haoyue Tang, Tao Li, Tao Qin, Wei Chen, Tie-Yan Liu
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
no code implementations • 2 Nov 2020 • Hua-Xing Chen, Wei Chen, Xiang Liu, Xiao-Hai Liu
We study the $P_{cs}(4459)^0$ recently observed by LHCb using the method of QCD sum rules.
High Energy Physics - Phenomenology High Energy Physics - Experiment
no code implementations • 30 Oct 2020 • Shuhao Xia, Jingyang Zhu, Yuhan Yang, Yong Zhou, Yuanming Shi, Wei Chen
In this paper, we consider federated learning (FL) over a noisy fading multiple access channel (MAC), where an edge server aggregates the local models transmitted by multiple end devices through over-the-air computation (AirComp).
no code implementations • 29 Oct 2020 • Wei Chen, BoWen Zhang, Shi Jin, Bo Ai, Zhangdui Zhong
Sparse signal recovery problems from noisy linear measurements appear in many areas of wireless communications.
no code implementations • 16 Oct 2020 • Wei Chen, Weiping Wang, Li Liu, Michael S. Lew
The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.
1 code implementation • 15 Oct 2020 • Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker, Michael Lew
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
no code implementations • 9 Oct 2020 • Min Zhao, Tiande Gao, Jie Chen, Wei Chen
In our work, we propose an NMF based unmixing framework which jointly uses a handcrafting regularizer and a learnt regularizer from data.
no code implementations • 28 Sep 2020 • Chuanbo Wang, Ye Guo, Wei Chen, Zeyun Yu
With the advance of deep learning, various neural network models have gained great success in image analysis including the recognition of intervertebral discs.
no code implementations • 16 Sep 2020 • Zijie Ye, Haozhe Wu, Jia Jia, Yaohua Bu, Wei Chen, Fanbo Meng, Yan-Feng Wang
Meanwhile, human choreographers design dance motions from music in a two-stage manner: they firstly devise multiple choreographic dance units (CAUs), each with a series of dance motions, and then arrange the CAU sequence according to the rhythm, melody and emotion of the music.
1 code implementation • 15 Sep 2020 • Wei Chen, Faez Ahmed
Despite their success in capturing complex distributions, existing generative models face three challenges when used for design problems: 1) generated designs have limited design space coverage, 2) the generator ignores design performance, and 3)~the new parameterization is unable to represent designs beyond training data.
no code implementations • 27 Aug 2020 • Dongming Han, Wei Chen, Rusheng Pan, Yijing Liu, Jiehui Zhou, Ying Xu, Tianye Zhang, Changjie Fan, Jianrong Tao, Xiaolong, Zhang
This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs.
Human-Computer Interaction Cryptography and Security Graphics
no code implementations • 25 Aug 2020 • Kartikeya Bhardwaj, Wei Chen, Radu Marculescu
In this paper, we first highlight three major challenges to large-scale adoption of deep learning at the edge: (i) Hardware-constrained IoT devices, (ii) Data security and privacy in the IoT era, and (iii) Lack of network-aware deep learning algorithms for distributed inference across multiple IoT devices.
no code implementations • 7 Aug 2020 • Zhiyuan Zhang, Binh-Son Hua, Wei Chen, Yibin Tian, Sai-Kit Yeung
We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive.
1 code implementation • 6 Aug 2020 • Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.
no code implementations • 30 Jul 2020 • Jiazhi Xia, Tianxiang Chen, Lei Zhang, Wei Chen, Yang Chen, Xiaolong Zhang, Cong Xie, Tobias Schreck
We build a prototype system based on our method, SMAP, to support the organization, computation, and exploration of secure joint embedding.
no code implementations • 30 Jul 2020 • Wei Zeng, Chengqiao Lin, Juncong Lin, Jincheng Jiang, Jiazhi Xia, Cagatay Turkay, Wei Chen
Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks.
no code implementations • 27 Jul 2020 • Yanna Bai, Wei Chen, Jie Chen, Weisi Guo
The linear inverse problem is fundamental to the development of various scientific areas.
1 code implementation • 21 Jul 2020 • Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Even further, we show that the proposed approach can achieve higher MI attack success rates on models trained with some data augmentation than the existing methods on models trained without data augmentation.
no code implementations • 7 Jul 2020 • Wei Chen, Faez Ahmed
Deep generative models have proven useful for automatic design synthesis and design space exploration.
no code implementations • ICML 2020 • Wei Chen, Xiaoming Sun, Jialin Zhang, Zhijie Zhang
We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data.
no code implementations • 1 Jul 2020 • Hythem Sidky, Wei Chen, Andrew L. Ferguson
Small integration time steps limit molecular dynamics (MD) simulations to millisecond time scales.
no code implementations • WS 2020 • Haiyang Xue, Yang Feng, Shuhao Gu, Wei Chen
In this paper, we propose a method to handle the two problems so as to generate robust translation to ASR errors.
no code implementations • 27 Jun 2020 • Liwei Wang, Siyu Tao, Ping Zhu, Wei Chen
With this model, we can easily obtain a continuous and differentiable transition between different microstructure concepts that can render gradient information for multiscale topology optimization.
no code implementations • 27 Jun 2020 • Liwei Wang, Yu-Chin Chan, Faez Ahmed, Zhao Liu, Ping Zhu, Wei Chen
For microstructure design, the tuning of mechanical properties and complex manipulations of microstructures are easily achieved by simple vector operations in the latent space.
no code implementations • 24 Jun 2020 • Qi Meng, Shiqi Gong, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
Specifically, we show that the covariance of the noise of SGD in the local region of the local minima is a quadratic function of the state.
no code implementations • 24 Jun 2020 • Jinhang Zuo, Xutong Liu, Carlee Joe-Wong, John C. S. Lui, Wei Chen
In this paper, we introduce a new Online Competitive Influence Maximization (OCIM) problem, where two competing items (e. g., products, news stories) propagate in the same network and influence probabilities on edges are unknown.
no code implementations • 23 Jun 2020 • Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao
For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.
1 code implementation • 21 Jun 2020 • Wei Chen, Kevin Chiu, Mark Fuge
The resulted new parameterization can accelerate design optimization convergence by improving the representation compactness while maintaining sufficient representation capacity.
no code implementations • 14 Jun 2020 • Yihan Du, Yuko Kuroki, Wei Chen
In this paper, we first study the problem of combinatorial pure exploration with full-bandit feedback (CPE-BL), where a learner is given a combinatorial action space $\mathcal{X} \subseteq \{0, 1\}^d$, and in each round the learner pulls an action $x \in \mathcal{X}$ and receives a random reward with expectation $x^{\top} \theta$, with $\theta \in \mathbb{R}^d$ a latent and unknown environment vector.
no code implementations • 4 Jun 2020 • Haichen Shen, Jared Roesch, Zhi Chen, Wei Chen, Yong Wu, Mu Li, Vin Sharma, Zachary Tatlock, Yida Wang
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.
no code implementations • ICML 2020 • Xiaoyu Chen, Kai Zheng, Zixin Zhou, Yunchang Yang, Wei Chen, Li-Wei Wang
In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting.
1 code implementation • 1 Jun 2020 • Yu-Chin Chan, Faez Ahmed, Li-Wei Wang, Wei Chen
In answer, we posit that a smaller yet diverse set of unit cells leads to scalable search and unbiased learning.
8 code implementations • Interspeech2020 2020 • Geng Yang, Shan Yang, Kai Liu, Peng Fang, Wei Chen, Lei Xie
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
no code implementations • 7 May 2020 • Siwei Fu, Kai Xiong, Xiaodong Ge, Siliang Tang, Wei Chen, Yingcai Wu
To address this challenge, we present a new dataset, called Quda, that aims to help V-NLIs recognize analytic tasks from free-form natural language by training and evaluating cutting-edge multi-label classification models.
no code implementations • 30 Apr 2020 • Jiayi Zhang, Chongyang Tao, Zhenjing Xu, Qiaojing Xie, Wei Chen, Rui Yan
Aiming at generating responses that approximate the ground-truth and receive high ranking scores from the discriminator, the two generators learn to generate improved highly relevant responses and competitive unobserved candidates respectively, while the discriminative ranker is trained to identify true responses from adversarial ones, thus featuring the merits of both generator counterparts.