Search Results for author: Yu Wang

Found 182 papers, 70 papers with code

基于规则的双重否定识别——以“不v1不v2”为例(Double Negative Recognition Based on Rules——Taking “不v1不v2” as an Example)

no code implementations CCL 2020 Yu Wang

“不v1不v2”是汉语中典型的双重否定结构形式之一, 它包括“不+助动词+不+v2”(不得不去)、“不+是+不v2”(不是不好)、述宾结构“不v1... 不v2”(不认为他不去)等多种双重否定结构, 情况复杂。本文以“不v1不v2”为例, 结合“元语否定”、“动词叙实性”、“否定焦点”等概念, 对“不v1不v2”进行了全面的考察, 制定了“不v1不v2”双重否定结构的识别策略。根据识别策略, 设计了双重否定自动识别程序, 并在此过程中补充了助动词表、非叙实动词表等词库。最终, 对28033句语料进行了识别, 识别正确率为97. 87%, 召回率约为93. 10%。

CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks

no code implementations ICLR 2019 Yu Wang, Fengjuan Gao, Amin Alipour, Linzhang Wang, Xuandong Li, Zhendong Su

Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.

NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING

no code implementations ICLR 2019 Yu Wang, Jack W. Stokes, Mady Marinescu

Antimalware products are a key component in detecting malware attacks, and their engines typically execute unknown programs in a sandbox prior to running them on the native operating system.

reinforcement-learning

HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction

no code implementations EMNLP 2020 Yu Wang, Yun Li, Hanghang Tong, Ziye Zhu

Specifically, we design (1) Head-Tail Detector based on the multi-head self-attention mechanism and bi-affine classifier to detect boundary tokens, and (2) Token Interaction Tagger based on traditional sequence labeling approaches to characterize the internal token connection within the boundary.

NER Nested Named Entity Recognition

Pseudo-Masked Language Models for Unified Language Model Pre-Training

1 code implementation ICML 2020 Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Jianfeng Gao, Songhao Piao, Ming Zhou, Hsiao-Wuen Hon

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).

Language Modelling Natural Language Understanding

Brachial Plexus Nerve Trunk Segmentation Using Deep Learning: A Comparative Study with Doctors' Manual Segmentation

no code implementations17 May 2022 Yu Wang, Binbin Zhu, Lingsi Kong, Jianlin Wang, Bin Gao, Jianhua Wang, Dingcheng Tian, YuDong Yao

With the help of deep learning methods, the automatic identification or segmentation of nerves can be realized, assisting doctors in completing nerve block anesthesia accurately and efficiently.

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

no code implementations14 May 2022 Wenhao Huang, Haifan Gong, huan zhang, Yu Wang, Haofeng Li, Guanbin Li, Hong Shen

CT-based bronchial tree analysis plays an important role in the computer-aided diagnosis for respiratory diseases, as it could provide structured information for clinicians.

Classification Graph Learning +2

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

no code implementations13 May 2022 Chaoqin Huang, Qinwei Xu, Yanfeng Wang, Yu Wang, Ya zhang

To extend the reconstruction-based anomaly detection architecture to the localized anomalies, we propose a self-supervised learning approach through random masking and then restoring, named Self-Supervised Masking (SSM) for unsupervised anomaly detection and localization.

Defect Detection Medical Diagnosis +2

GypSum: Learning Hybrid Representations for Code Summarization

1 code implementation26 Apr 2022 Yu Wang, Yu Dong, Xuesong Lu, Aoying Zhou

Current deep learning models for code summarization generally follow the principle in neural machine translation and adopt the encoder-decoder framework, where the encoder learns the semantic representations from source code and the decoder transforms the learnt representations into human-readable text that describes the functionality of code snippets.

Code Summarization Graph Attention +3

R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction

no code implementations21 Apr 2022 Yu Wang, Shuo Ye, Shujian Yu, Xinge You

In this paper, we present a novel approach for FGVC, which can simultaneously make use of partial yet sufficient discriminative information in environmental cues and also compress the redundant information in class-token with respect to the target.

Fine-Grained Visual Categorization

Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data

1 code implementation7 Apr 2022 Zeyu Sun, Monica G. Bobra, Xiantong Wang, Yu Wang, Hu Sun, Tamas Gombosi, Yang Chen, Alfred Hero

We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours.

Primal-dual Estimator Learning: an Offline Constrained Moving Horizon Estimation Method with Feasibility and Near-optimality Guarantees

no code implementations6 Apr 2022 Wenhan Cao, Jingliang Duan, Shengbo Eben Li, Chen Chen, Chang Liu, Yu Wang

Both the primal and dual estimators are learned from data using supervised learning techniques, and the explicit sample size is provided, which enables us to guarantee the quality of each learned estimator in terms of feasibility and optimality.

Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation

1 code implementation19 Mar 2022 Junwen Pan, Pengfei Zhu, Kaihua Zhang, Bing Cao, Yu Wang, Dingwen Zhang, Junwei Han, QinGhua Hu

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.

Semi-Supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance

no code implementations18 Mar 2022 Tianchen Zhao, Niansong Zhang, Xuefei Ning, He Wang, Li Yi, Yu Wang

We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers.

3D Semantic Segmentation

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation

1 code implementation17 Mar 2022 Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Lichao Sun

Federated Learning (FL) on knowledge graphs (KGs) has yet to be as well studied as other domains, such as computer vision and natural language processing.

Entity Embeddings Federated Learning +2

A Data Augmentation Method for Fully Automatic Brain Tumor Segmentation

no code implementations13 Feb 2022 Yu Wang, Yarong Ji, Hongbing Xiao

Then the tensor was mapped to a matrix which was used to mix the one-hot encoded labels of the above image patches.

Brain Tumor Segmentation Data Augmentation +1

ChemicalX: A Deep Learning Library for Drug Pair Scoring

1 code implementation10 Feb 2022 Benedek Rozemberczki, Charles Tapley Hoyt, Anna Gogleva, Piotr Grabowski, Klas Karis, Andrej Lamov, Andriy Nikolov, Sebastian Nilsson, Michael Ughetto, Yu Wang, Tyler Derr, Benjamin M Gyori

In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task.

Evaluating the impact of quarantine measures on COVID-19 spread

no code implementations9 Feb 2022 Renquan Zhang, Yu Wang, Zheng Lv, Sen Pei

We generate counterfactual simulations to estimate effectiveness of quarantine measures.

Decision Making

Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network

1 code implementation7 Feb 2022 Liangwei Yang, Zhiwei Liu, Yu Wang, Chen Wang, Ziwei Fan, Philip S. Yu

We conduct a comprehensive analysis of users' online game behaviors, which motivates the necessity of handling those three characteristics in the online game recommendation.

Recommendation Systems

Improving Out-of-Distribution Robustness via Selective Augmentation

1 code implementation2 Jan 2022 Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn

Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.

Transferrable Contrastive Learning for Visual Domain Adaptation

no code implementations14 Dec 2021 Yang Chen, Yingwei Pan, Yu Wang, Ting Yao, Xinmei Tian, Tao Mei

From this point, we present a particular paradigm of self-supervised learning tailored for domain adaptation, i. e., Transferrable Contrastive Learning (TCL), which links the SSL and the desired cross-domain transferability congruently.

Contrastive Learning Domain Adaptation +1

A Style and Semantic Memory Mechanism for Domain Generalization

no code implementations ICCV 2021 Yang Chen, Yu Wang, Yingwei Pan, Ting Yao, Xinmei Tian, Tao Mei

Correspondingly, we also propose a novel "jury" mechanism, which is particularly effective in learning useful semantic feature commonalities among domains.

Domain Generalization

Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward

no code implementations12 Dec 2021 Weilin Liu, Ye Mu, Chao Yu, Xuefei Ning, Zhong Cao, Yi Wu, Shuang Liang, Huazhong Yang, Yu Wang

These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.

Autonomous Driving Multi-agent Reinforcement Learning

Multiway Ensemble Kalman Filter

1 code implementation8 Dec 2021 Yu Wang, Alfred Hero

In this work, we study the emergence of sparsity and multiway structures in second-order statistical characterizations of dynamical processes governed by partial differential equations (PDEs).

Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess

no code implementations NeurIPS 2021 Reid McIlroy-Young, Yu Wang, Siddhartha Sen, Jon Kleinberg, Ashton Anderson

The advent of machine learning models that surpass human decision-making ability in complex domains has initiated a movement towards building AI systems that interact with humans.

Decision Making

Imbalanced Graph Classification via Graph-of-Graph Neural Networks

1 code implementation1 Dec 2021 Yu Wang, Yuying Zhao, Neil Shah, Tyler Derr

Graph Neural Networks (GNNs) have achieved unprecedented success in learning graph representations to identify categorical labels of graphs.

Classification Graph Classification +1

Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking

no code implementations23 Nov 2021 Pengfei Zhu, Hongtao Yu, Kaihua Zhang, Yu Wang, Shuai Zhao, Lei Wang, Tianzhu Zhang, QinGhua Hu

To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.

Frame Visual Object Tracking +1

Learning Dynamic Preference Structure Embedding From Temporal Networks

1 code implementation23 Nov 2021 Tongya Zheng, Zunlei Feng, Yu Wang, Chengchao Shen, Mingli Song, Xingen Wang, Xinyu Wang, Chun Chen, Hao Xu

Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion.

Graph Sampling

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

1 code implementation NeurIPS 2021 Jiayu Chen, Yuanxin Zhang, Yuanfan Xu, Huimin Ma, Huazhong Yang, Jiaming Song, Yu Wang, Yi Wu

We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution.

Multi-agent Reinforcement Learning

Meta-learning with an Adaptive Task Scheduler

1 code implementation NeurIPS 2021 Huaxiu Yao, Yu Wang, Ying WEI, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, Chelsea Finn

In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.

Drug Discovery Meta-Learning

Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification

1 code implementation22 Oct 2021 Yu Wang, Charu Aggarwal, Tyler Derr

Recent years have witnessed the significant success of applying graph neural networks (GNNs) in learning effective node representations for classification.

Classification Metric Learning +2

Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective

no code implementations18 Oct 2021 Hengrui Zhang, Zhongming Yu, Guohao Dai, Guyue Huang, Yufei Ding, Yuan Xie, Yu Wang

The same data are propagated through the graph structure to perform the same neural operation multiple times in GNNs, leading to redundant computation which accounts for 92. 4% of total operators.

Learning Efficient Multi-Agent Cooperative Visual Exploration

no code implementations12 Oct 2021 Chao Yu, Xinyi Yang, Jiaxuan Gao, Huazhong Yang, Yu Wang, Yi Wu

In this paper, we extend the state-of-the-art single-agent visual navigation method, Active Neural SLAM (ANS), to the multi-agent setting by introducing a novel RL-based planning module, Multi-agent Spatial Planner (MSP). MSP leverages a transformer-based architecture, Spatial-TeamFormer, which effectively captures spatial relations and intra-agent interactions via hierarchical spatial self-attentions.

Visual Navigation

AutoNF: Automated Architecture Optimization of Normalizing Flows Using a Mixture Distribution Formulation

no code implementations29 Sep 2021 Yu Wang, Jan Drgona, Jiaxin Zhang, Karthik Somayaji NS, Frank Y Liu, Malachi Schram, Peng Li

Although various flow models based on different transformations have been proposed, there still lacks a quantitative analysis of performance-cost trade-offs between different flows as well as a systematic way of constructing the best flow architecture.

BoolNet: Streamlining Binary Neural Networks Using Binary Feature Maps

no code implementations29 Sep 2021 Nianhui Guo, Joseph Bethge, Haojin Yang, Kai Zhong, Xuefei Ning, Christoph Meinel, Yu Wang

Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts, often based on specialized model designs using additional 32-bit components.

Efficient Context-Aware Network for Abdominal Multi-organ Segmentation

1 code implementation22 Sep 2021 Fan Zhang, Yu Wang, Hua Yang

For the context block, we propose strip pooling module to capture anisotropic and long-range contextual information, which exists in abdominal scene.

Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models

1 code implementation28 Aug 2021 Yu Wang, Fang Liu, Daniele E. Schiavazzi

To reduce the computational cost without sacrificing inferential accuracy, we propose Normalizing Flow with Adaptive Surrogate (NoFAS), an optimization strategy that alternatively updates the normalizing flow parameters and surrogate model parameters.

Bayesian Inference Variational Inference

DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN

1 code implementation26 Aug 2021 Yu Wang, Zhiwei Liu, Ziwei Fan, Lichao Sun, Philip S. Yu

In the information explosion era, recommender systems (RSs) are widely studied and applied to discover user-preferred information.

Knowledge Graphs Recommendation Systems

Tree Decomposed Graph Neural Network

1 code implementation25 Aug 2021 Yu Wang, Tyler Derr

Nevertheless, iterative propagation restricts the information of higher-layer neighborhoods to be transported through and fused with the lower-layer neighborhoods', which unavoidably results in feature smoothing between neighborhoods in different layers and can thus compromise the performance, especially on heterophily networks.

Node Classification

A Low Rank Promoting Prior for Unsupervised Contrastive Learning

no code implementations5 Aug 2021 Yu Wang, Jingyang Lin, Qi Cai, Yingwei Pan, Ting Yao, Hongyang Chao, Tao Mei

In this paper, we construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning, referred to as LORAC.

Contrastive Learning Image Classification +4

Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL

no code implementations ACL 2021 Jiaqi Guo, Ziliang Si, Yu Wang, Qian Liu, Ming Fan, Jian-Guang Lou, Zijiang Yang, Ting Liu

However, we identify two biases in existing datasets for XDTS: (1) a high proportion of context-independent questions and (2) a high proportion of easy SQL queries.

Text-To-Sql

MedAI at SemEval-2021 Task 10: Negation-aware Pre-training for Source-free Negation Detection Domain Adaptation

no code implementations SEMEVAL 2021 Jinquan Sun, Qi Zhang, Yu Wang, Lei Zhang

Due to the increasing concerns for data privacy, source-free unsupervised domain adaptation attracts more and more research attention, where only a trained source model is assumed to be available, while the labeled source data remain private.

Negation Detection Unsupervised Domain Adaptation

United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks

1 code implementation28 Jul 2021 Sindi Shkodrani, Yu Wang, Marco Manfredi, Nóra Baka

Attempts of learning from hierarchical taxonomies in computer vision have been mostly focusing on image classification.

Classification Image Classification +1

Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification

no code implementations27 Jul 2021 Yu Wang, Yuesong Shen, Daniel Cremers

To learn the direct influence among output nodes in a graph, we propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field.

Node Classification

BoolNet: Minimizing The Energy Consumption of Binary Neural Networks

1 code implementation13 Jun 2021 Nianhui Guo, Joseph Bethge, Haojin Yang, Kai Zhong, Xuefei Ning, Christoph Meinel, Yu Wang

Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts.

An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interaction

no code implementations6 Jun 2021 Yu Wang, Yilin Shen, Hongxia Jin

In this paper, we introduce a novel multi-step spoken language understanding system based on adversarial learning that can leverage the multiround user's feedback to update slot values.

Dialogue State Tracking Frame +2

A Coarse to Fine Question Answering System based on Reinforcement Learning

no code implementations1 Jun 2021 Yu Wang, Hongxia Jin

In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning which can efficiently processes documents with different lengths by choosing appropriate actions.

Question Answering reinforcement-learning

SG-PALM: a Fast Physically Interpretable Tensor Graphical Model

1 code implementation26 May 2021 Yu Wang, Alfred Hero

We propose a new graphical model inference procedure, called SG-PALM, for learning conditional dependency structure of high-dimensional tensor-variate data.

Spatio-Temporal Forecasting

Learning Robust Recommenders through Cross-Model Agreement

no code implementations20 May 2021 Yu Wang, Xin Xin, Zaiqiao Meng, Xiangnan He, Joemon Jose, Fuli Feng

A noisy negative example which is uninteracted because of unawareness of the user could also denote potential positive user preference.

Denoising Recommendation Systems

Integrated Communication and Navigation for Ultra-Dense LEO Satellite Networks: Vision, Challenges and Solutions

no code implementations19 May 2021 Yu Wang, Hejia Luo, Ying Chen, Jun Wang, Rong Li, Bin Wang

Next generation beyond 5G networks are expected to provide both Terabits per second data rate communication services and centimeter-level accuracy localization services in an efficient, seamless and cost-effective manner.

Domain-Specific Suppression for Adaptive Object Detection

no code implementations CVPR 2021 Yu Wang, Rui Zhang, Shuo Zhang, Miao Li, Yangyang Xia, Xishan Zhang, Shaoli Liu

The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one.

Domain Adaptation Object Detection

Unsupervised Remote Sensing Super-Resolution via Migration Image Prior

1 code implementation8 May 2021 JiaMing Wang, Zhenfeng Shao, Tao Lu, Xiao Huang, Ruiqian Zhang, Yu Wang

Despite their success, however, low/high spatial resolution pairs are usually difficult to obtain in satellites with a high temporal resolution, making such approaches in SR impractical to use.

Super-Resolution

Membership Inference Attacks on Knowledge Graphs

no code implementations16 Apr 2021 Yu Wang, Lifu Huang, Philip S. Yu, Lichao Sun

Membership inference attacks (MIAs) infer whether a specific data record is used for target model training.

Inference Attack Knowledge Graph Completion +4

Adversarial Robustness under Long-Tailed Distribution

1 code implementation CVPR 2021 Tong Wu, Ziwei Liu, Qingqiu Huang, Yu Wang, Dahua Lin

We then perform a systematic study on existing long-tailed recognition methods in conjunction with the adversarial training framework.

Adversarial Robustness

ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of Kaldi

1 code implementation3 Apr 2021 Yu Wang, Chee Siang Leow, Akio Kobayashi, Takehito Utsuro, Hiromitsu Nishizaki

This paper describes the ExKaldi-RT online automatic speech recognition (ASR) toolkit that is implemented based on the Kaldi ASR toolkit and Python language.

Automatic Speech Recognition

Model-Free Learning of Safe yet Effective Controllers

no code implementations26 Mar 2021 Alper Kamil Bozkurt, Yu Wang, Miroslav Pajic

We study the problem of learning safe control policies that are also effective; i. e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control performance.

reinforcement-learning

FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning

no code implementations24 Mar 2021 Minxue Tang, Xuefei Ning, Yitu Wang, Jingwei Sun, Yu Wang, Hai Li, Yiran Chen

In this work, we propose FedCor -- an FL framework built on a correlation-based client selection strategy, to boost the convergence rate of FL.

Federated Learning

Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction

2 code implementations13 Mar 2021 Shaowei Chen, Yu Wang, Jie Liu, Yuelin Wang

Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining.

Aspect Sentiment Triplet Extraction Machine Reading Comprehension +1

Learning-Based Vulnerability Analysis of Cyber-Physical Systems

no code implementations10 Mar 2021 Amir Khazraei, Spencer Hallyburton, Qitong Gao, Yu Wang, Miroslav Pajic

This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems (CPS).

Anomaly Detection

Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

2 code implementations ICLR 2021 Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, Yi Wu

We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.

The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games

6 code implementations2 Mar 2021 Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, Yi Wu

Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings.

Starcraft Starcraft II

Provable Boolean Interaction Recovery from Tree Ensemble obtained via Random Forests

no code implementations23 Feb 2021 Merle Behr, Yu Wang, Xiao Li, Bin Yu

Iterative Random Forests (iRF) use a tree ensemble from iteratively modified RF to obtain predictive and stable non-linear or Boolean interactions of features.

Statistics Theory Statistics Theory

Stability of scar states in 2D PXP model against random disorders

no code implementations16 Feb 2021 Ke Huang, Yu Wang, Xiao Li

Recently a class of quantum systems exhibiting weak ergodicity breaking has attracted much attention.

Disordered Systems and Neural Networks Statistical Mechanics

Dissecting Energy Budget of a Gamma-Ray Burst Fireball

no code implementations9 Feb 2021 Bing Zhang, Yu Wang, Liang Li

The jet composition and radiative efficiency of GRBs are poorly constrained from the data.

High Energy Astrophysical Phenomena

Learning Optimal Strategies for Temporal Tasks in Stochastic Games

no code implementations8 Feb 2021 Alper Kamil Bozkurt, Yu Wang, Michael M. Zavlanos, Miroslav Pajic

By deriving distinct rewards and discount factors from the acceptance condition of the DPA, we reduce the maximization of the worst-case probability of satisfying the LTL specification into the maximization of a discounted reward objective in the product game; this allows for the use of model-free RL algorithms to learn an optimal controller strategy.

Enabling Lower-Power Charge-Domain Nonvolatile In-Memory Computing with Ferroelectric FETs

no code implementations2 Feb 2021 Guodong Yin, Yi Cai, Juejian Wu, Zhengyang Duan, Zhenhua Zhu, Yongpan Liu, Yu Wang, Huazhong Yang, Xueqing Li

Compute-in-memory (CiM) is a promising approach to alleviating the memory wall problem for domain-specific applications.

Emerging Technologies

Machine Learning for Electronic Design Automation: A Survey

1 code implementation10 Jan 2021 Guyue Huang, Jingbo Hu, Yifan He, Jialong Liu, Mingyuan Ma, Zhaoyang Shen, Juejian Wu, Yuanfan Xu, Hengrui Zhang, Kai Zhong, Xuefei Ning, Yuzhe ma, HaoYu Yang, Bei Yu, Huazhong Yang, Yu Wang

With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing.

Explore the Potential of CNN Low Bit Training

no code implementations1 Jan 2021 Kai Zhong, Xuefei Ning, Tianchen Zhao, Zhenhua Zhu, Shulin Zeng, Guohao Dai, Yu Wang, Huazhong Yang

Through this dynamic precision framework, we can reduce the bit-width of convolution, which is the most computational cost, while keeping the training process close to the full precision floating-point training.

Quantization

Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms

no code implementations1 Jan 2021 Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, Yi Wu

We benchmark commonly used multi-agent deep reinforcement learning (MARL) algorithms on a variety of cooperative multi-agent games.

reinforcement-learning Starcraft

Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach

1 code implementation22 Dec 2020 Xuefei Ning, Junbo Zhao, Wenshuo Li, Tianchen Zhao, Yin Zheng, Huazhong Yang, Yu Wang

In this paper, considering scenarios with capacity budget, we aim to discover adversarially robust architecture at targeted capacities.

Neural Architecture Search

TRACE: Early Detection of Chronic Kidney Disease Onset with Transformer-Enhanced Feature Embedding

no code implementations3 Dec 2020 Yu Wang, Ziqiao Guan, Wei Hou, Fusheng Wang

The early detection of CKD faces challenges of insufficient medical histories of positive patients and complicated risk factors.

Disease Prediction

Learning to Adapt to Evolving Domains

1 code implementation NeurIPS 2020 Hong Liu, Mingsheng Long, Jianmin Wang, Yu Wang

(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.

Meta-Learning Transfer Learning +1

aw_nas: A Modularized and Extensible NAS framework

1 code implementation25 Nov 2020 Xuefei Ning, Changcheng Tang, Wenshuo Li, Songyi Yang, Tianchen Zhao, Niansong Zhang, Tianyi Lu, Shuang Liang, Huazhong Yang, Yu Wang

Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner.

Adversarial Robustness Neural Architecture Search

Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes

no code implementations18 Nov 2020 Feng Gao, Jincheng Yu, Hao Shen, Yu Wang, Huazhong Yang

Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots.

A Learning-Based Tune-Free Control Framework for Large Scale Autonomous Driving System Deployment

no code implementations9 Nov 2020 Yu Wang, Shu Jiang, Weiman Lin, Yu Cao, Longtao Lin, Jiangtao Hu, Jinghao Miao, Qi Luo

This paper presents the design of a tune-free (human-out-of-the-loop parameter tuning) control framework, aiming at accelerating large scale autonomous driving system deployed on various vehicles and driving environments.

Autonomous Driving

Face Hallucination via Split-Attention in Split-Attention Network

1 code implementation22 Oct 2020 Tao Lu, Yuanzhi Wang, Yanduo Zhang, Yu Wang, Wei Liu, Zhongyuan Wang, Junjun Jiang

However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).

Face Detection Face Hallucination +3

Joint Contrastive Learning with Infinite Possibilities

1 code implementation NeurIPS 2020 Qi Cai, Yu Wang, Yingwei Pan, Ting Yao, Tao Mei

This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling.

Contrastive Learning

A Survey of FPGA-Based Robotic Computing

no code implementations13 Sep 2020 Zishen Wan, Bo Yu, Thomas Yuang Li, Jie Tang, Yuhao Zhu, Yu Wang, Arijit Raychowdhury, Shaoshan Liu

On the other hand, FPGA-based robotic accelerators are becoming increasingly competitive alternatives, especially in latency-critical and power-limited scenarios.

Autonomous Vehicles Legged Robots

SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context

no code implementations11 Sep 2020 Mark Cartwright, Jason Cramer, Ana Elisa Mendez Mendez, Yu Wang, Ho-Hsiang Wu, Vincent Lostanlen, Magdalena Fuentes, Graham Dove, Charlie Mydlarz, Justin Salamon, Oded Nov, Juan Pablo Bello

In this article, we describe our data collection procedure and propose evaluation metrics for multilabel classification of urban sound tags.

Shift Equivariance in Object Detection

no code implementations13 Aug 2020 Marco Manfredi, Yu Wang

Robustness to small image translations is a highly desirable property for object detectors.

Object Detection

Evaluating Efficient Performance Estimators of Neural Architectures

1 code implementation NeurIPS 2021 Xuefei Ning, Changcheng Tang, Wenshuo Li, Zixuan Zhou, Shuang Liang, Huazhong Yang, Yu Wang

Conducting efficient performance estimations of neural architectures is a major challenge in neural architecture search (NAS).

Neural Architecture Search

Probabilistic Conformance for Cyber-Physical Systems

no code implementations3 Aug 2020 Yu Wang, Mojtaba Zarei, Borzoo Bonakdarpoor, Miroslav Pajic

In system analysis, conformance indicates that two systems simultaneously satisfy the same set of specifications of interest; thus, the results from analyzing one system automatically transfer to the other, or one system can safely replace the other in practice.

Physical Adversarial Attack on Vehicle Detector in the Carla Simulator

no code implementations31 Jul 2020 Tong Wu, Xuefei Ning, Wenshuo Li, Ranran Huang, Huazhong Yang, Yu Wang

In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild.

Adversarial Attack

Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

1 code implementation ECCV 2020 Tong Wu, Qingqiu Huang, Ziwei Liu, Yu Wang, Dahua Lin

We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions.

General Classification Multi-Label Classification

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification

no code implementations13 Jul 2020 Yucan Zhou, Yu Wang, Jianfei Cai, Yu Zhou, QinGhua Hu, Weiping Wang

Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.

General Classification Meta-Learning

GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks

2 code implementations7 Jul 2020 Guyue Huang, Guohao Dai, Yu Wang, Huazhong Yang

GE-SpMM performs SpMM-like operation on sparse matrices represented in the most common Compressed Sparse Row (CSR) format, so it can be embedded in GNN frameworks with no preprocessing overheads and support general GNN algorithms.

Distributed, Parallel, and Cluster Computing

Monitoring Depression Trend on Twitter during the COVID-19 Pandemic

no code implementations1 Jul 2020 Yi-Peng Zhang, Hanjia Lyu, Yubao Liu, Xiyang Zhang, Yu Wang, Jiebo Luo

The COVID-19 pandemic has severely affected people's daily lives and caused tremendous economic loss worldwide.

Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction

1 code implementation ACL 2020 Shaowei Chen, Jie Liu, Yu Wang, Wenzheng Zhang, Ziming Chi

The opinion entity extraction unit and the relation detection unit are developed as two channels to extract opinion entities and relations simultaneously.

Entity Extraction using GAN Opinion Mining +1

1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation

no code implementations28 Jun 2020 Zhuangzhuang Ding, Yihan Hu, Runzhou Ge, Li Huang, Sijia Chen, Yu Wang, Jie Liao

We proposed a one-stage, anchor-free and NMS-free 3D point cloud object detector AFDet, using object key-points to encode the 3D attributes, and to learn an end-to-end point cloud object detection without the need of hand-engineering or learning the anchors.

Domain Adaptation Object Detection

1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking

no code implementations28 Jun 2020 Yu Wang, Sijia Chen, Li Huang, Runzhou Ge, Yihan Hu, Zhuangzhuang Ding, Jie Liao

This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges.

3D Multi-Object Tracking

AFDet: Anchor Free One Stage 3D Object Detection

4 code implementations23 Jun 2020 Runzhou Ge, Zhuangzhuang Ding, Yihan Hu, Yu Wang, Sijia Chen, Li Huang, Yuan Li

High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving.

3D Object Detection Autonomous Driving

Deep Learning for Stable Monotone Dynamical Systems

no code implementations11 Jun 2020 Yu Wang, Qitong Gao, Miroslav Pajic

Monotone systems, originating from real-world (e. g., biological or chemical) applications, are a class of dynamical systems that preserves a partial order of system states over time.

Learning a Unified Sample Weighting Network for Object Detection

1 code implementation CVPR 2020 Qi Cai, Yingwei Pan, Yu Wang, Jingen Liu, Ting Yao, Tao Mei

To this end, we devise a general loss function to cover most region-based object detectors with various sampling strategies, and then based on it we propose a unified sample weighting network to predict a sample's task weights.

General Classification Object Detection

Exploring the Potential of Low-bit Training of Convolutional Neural Networks

no code implementations4 Jun 2020 Kai Zhong, Xuefei Ning, Guohao Dai, Zhenhua Zhu, Tianchen Zhao, Shulin Zeng, Yu Wang, Huazhong Yang

For training a variety of models on CIFAR-10, using 1-bit mantissa and 2-bit exponent is adequate to keep the accuracy loss within $1\%$.

Quantization

Precisely Predicting Acute Kidney Injury with Convolutional Neural Network Based on Electronic Health Record Data

no code implementations27 May 2020 Yu Wang, Junpeng Bao, JianQiang Du, Yongfeng Li

Compared with the existing AKI predictors, the predictor in this work greatly improves the precision of early prediction of AKI by using the Convolutional Neural Network architecture and a more concise input vector.

Learning Semantic Program Embeddings with Graph Interval Neural Network

no code implementations18 May 2020 Yu Wang, Fengjuan Gao, Linzhang Wang, Ke Wang

We have also created a neural bug detector based on GINN to catch null pointer deference bugs in Java code.

Method name prediction Variable misuse

Curating a COVID-19 data repository and forecasting county-level death counts in the United States

1 code implementation16 May 2020 Nick Altieri, Rebecca L. Barter, James Duncan, Raaz Dwivedi, Karl Kumbier, Xiao Li, Robert Netzorg, Briton Park, Chandan Singh, Yan Shuo Tan, Tiffany Tang, Yu Wang, Chao Zhang, Bin Yu

We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.

COVID-19 Tracking Decision Making +2

Energy-Aware DNN Graph Optimization

1 code implementation12 May 2020 Yu Wang, Rong Ge, Shuang Qiu

Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices.

A Comprehensive Survey of Grammar Error Correction

no code implementations2 May 2020 Yu Wang, Yuelin Wang, Jie Liu, Zhuo Liu

More importantly, we discuss four kinds of basic approaches, including statistical machine translation based approach, neural machine translation based approach, classification based approach and language model based approach, six commonly applied performance boosting techniques for GEC systems and two data augmentation methods.

Data Augmentation Language Modelling +2

In the Eyes of the Beholder: Analyzing Social Media Use of Neutral and Controversial Terms for COVID-19

no code implementations21 Apr 2020 Long Chen, Hanjia Lyu, Tongyu Yang, Yu Wang, Jiebo Luo

To model the substantive difference of tweets with controversial terms and those with non-controversial terms, we apply topic modeling and LIWC-based sentiment analysis.

Sentiment Analysis

The Ivory Tower Lost: How College Students Respond Differently than the General Public to the COVID-19 Pandemic

no code implementations21 Apr 2020 Viet Duong, Phu Pham, Tongyu Yang, Yu Wang, Jiebo Luo

Recently, the pandemic of the novel Coronavirus Disease-2019 (COVID-19) has presented governments with ultimate challenges.

Adversarial Training for Large Neural Language Models

2 code implementations20 Apr 2020 Xiaodong Liu, Hao Cheng, Pengcheng He, Weizhu Chen, Yu Wang, Hoifung Poon, Jianfeng Gao

In natural language processing (NLP), pre-training large neural language models such as BERT have demonstrated impressive gain in generalization for a variety of tasks, with further improvement from adversarial fine-tuning.

Ranked #3 on Natural Language Inference on ANLI test (using extra training data)

Natural Language Inference Natural Language Understanding

Robust Beamforming Design for Intelligent Reflecting Surface Aided Cognitive Radio Systems with Imperfect Cascaded CSI

no code implementations9 Apr 2020 Lei Zhang, Cunhua Pan, Yu Wang, Hong Ren, Kezhi Wang

Simulation results verify the efficiency of the proposed algorithms and reveal the impacts of CSI uncertainties on ST's minimum transmit power and feasibility rate of the optimization problems.

DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation

1 code implementation ECCV 2020 Xuefei Ning, Tianchen Zhao, Wenshuo Li, Peng Lei, Yu Wang, Huazhong Yang

In budgeted pruning, how to distribute the resources across layers (i. e., sparsity allocation) is the key problem.

Differential Privacy for Sequential Algorithms

no code implementations1 Apr 2020 Yu Wang, Hussein Sibai, Sayan Mitra, Geir E. Dullerud

Using the two examples: sequential probability ratio test and sequential empirical risk minimization, we show that the number of steps such algorithms execute before termination can jeopardize the differential privacy of the input data in a similar fashion as their outputs, and it is impossible to use the usual Laplace mechanism to achieve standard differentially private in these examples.

Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning

no code implementations1 Apr 2020 Yu Wang, Nima Roohi, Matthew West, Mahesh Viswanathan, Geir E. Dullerud

Probabilistic Computation Tree Logic (PCTL) is frequently used to formally specify control objectives such as probabilistic reachability and safety.

Q-Learning reinforcement-learning

Enabling Efficient and Flexible FPGA Virtualization for Deep Learning in the Cloud

no code implementations26 Mar 2020 Shulin Zeng, Guohao Dai, Hanbo Sun, Kai Zhong, Guangjun Ge, Kaiyuan Guo, Yu Wang, Huazhong Yang

Currently, the majority of FPGA-based DNN accelerators in the cloud run in a time-division multiplexing way for multiple users sharing a single FPGA, and require re-compilation with $\sim$100 s overhead.

FTT-NAS: Discovering Fault-Tolerant Convolutional Neural Architecture

no code implementations20 Mar 2020 Xuefei Ning, Guangjun Ge, Wenshuo Li, Zhenhua Zhu, Yin Zheng, Xiaoming Chen, Zhen Gao, Yu Wang, Huazhong Yang

By inspecting the discovered architectures, we find that the operation primitives, the weight quantization range, the capacity of the model, and the connection pattern have influences on the fault resilience capability of NN models.

Neural Architecture Search Quantization

UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

2 code implementations28 Feb 2020 Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Songhao Piao, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).

Ranked #3 on Question Generation on SQuAD1.1 (using extra training data)

Abstractive Text Summarization Language Modelling +2

Application of Pre-training Models in Named Entity Recognition

no code implementations9 Feb 2020 Yu Wang, Yining Sun, Zuchang Ma, Lisheng Gao, Yang Xu, Ting Sun

Then, we apply these pre-training models to a NER task by fine-tuning, and compare the effects of the different model architecture and pre-training tasks on the NER task.

Named Entity Recognition NER

The Sylvester Graphical Lasso (SyGlasso)

1 code implementation1 Feb 2020 Yu Wang, Byoungwook Jang, Alfred Hero

We apply the SyGlasso to an electroencephalography (EEG) study to compare the brain connectivity of alcoholic and nonalcoholic subjects.

EEG

Communication Lower Bound in Convolution Accelerators

no code implementations8 Nov 2019 Xiaoming Chen, Yinhe Han, Yu Wang

Evaluations based on the 65nm technology demonstrate that the proposed architecture nearly reaches the theoretical minimum communication in a three-level memory hierarchy and it is computation dominant.

Distributed, Parallel, and Cluster Computing Hardware Architecture

Review of Learning-based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps between Self-driving and Traffic Congestion

no code implementations2 Oct 2019 Hao Zhou, Jorge Laval, Anye Zhou, Yu Wang, Wenchao Wu, Zhu Qing, Srinivas Peeta

Some suggestions towards congestion mitigation for future mMP studies are proposed: i) enrich data collection to facilitate the congestion learning, ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and iii) integrate domain knowledge from the traditional car following (CF) theory to improve the string stability of mMP.

Autonomous Vehicles Imitation Learning +1

Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning

1 code implementation16 Sep 2019 Alper Kamil Bozkurt, Yu Wang, Michael M. Zavlanos, Miroslav Pajic

We present a reinforcement learning (RL) framework to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP).

Motion Planning reinforcement-learning

Single Training Dimension Selection for Word Embedding with PCA

no code implementations IJCNLP 2019 Yu Wang

In this paper, we present a fast and reliable method based on PCA to select the number of dimensions for word embeddings.

Question Answering Sentiment Analysis +1

New Era of Deeplearning-Based Malware Intrusion Detection: The Malware Detection and Prediction Based On Deep Learning

no code implementations19 Jul 2019 Shuqiang Lu, Lingyun Ying, Wenjie Lin, Yu Wang, Meining Nie, Kaiwen Shen, Lu Liu, Haixin Duan

With the development of artificial intelligence algorithms like deep learning models and the successful applications in many different fields, further similar trails of deep learning technology have been made in cyber security area.

General Classification Intrusion Detection +1

Learning a Static Bug Finder from Data

1 code implementation12 Jul 2019 Yu Wang, Fengjuan Gao, Linzhang Wang, Ke Wang

In a cross-project prediction task, three neural bug detectors we instantiate from NeurSA are effective in catching null pointer dereference, array index out of bound and class cast bugs in unseen code.

Frame

A Debiased MDI Feature Importance Measure for Random Forests

3 code implementations NeurIPS 2019 Xiao Li, Yu Wang, Sumanta Basu, Karl Kumbier, Bin Yu

Based on the original definition of MDI by Breiman et al. for a single tree, we derive a tight non-asymptotic bound on the expected bias of MDI importance of noisy features, showing that deep trees have higher (expected) feature selection bias than shallow ones.

Feature Importance Selection bias

ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

1 code implementation24 Jun 2019 Yu Wang, Quan Zhou, Xiaofu Wu

The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).

Real-Time Semantic Segmentation

Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift

1 code implementation7 Jun 2019 Xudong Sun, Alexej Gossmann, Yu Wang, Bernd Bischl

A novel variational inference based resampling framework is proposed to evaluate the robustness and generalization capability of deep learning models with respect to distribution shift.

Domain Generalization General Classification +3

Contribution of Radio Halos to the Foreground for SKA EoR Experiments

3 code implementations14 May 2019 Weitian Li, Haiguang Xu, Zhixian Ma, Dan Hu, Zhenghao Zhu, Chenxi Shan, Jingying Wang, Junhua Gu, Dongchao Zheng, Xiaoli Lian, Qian Zheng, Yu Wang, Jie Zhu, Xiang-Ping Wu

The overwhelming foreground contamination is one of the primary impediments to probing the EoR through measuring the redshifted 21 cm signal.

Cosmology and Nongalactic Astrophysics

Unified Language Model Pre-training for Natural Language Understanding and Generation

8 code implementations NeurIPS 2019 Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.

Ranked #2 on Generative Question Answering on CoQA (using extra training data)

Abstractive Text Summarization Document Summarization +6

Transferrable Prototypical Networks for Unsupervised Domain Adaptation

no code implementations CVPR 2019 Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, Tao Mei

Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar.

Unsupervised Domain Adaptation

Generalizable control for quantum parameter estimation through reinforcement learning

1 code implementation25 Apr 2019 Han Xu, Junning Li, Liqiang Liu, Yu Wang, Haidong Yuan, Xin Wang

Measurement and estimation of parameters are essential for science and engineering, where one of the main quests is to find systematic schemes that can achieve high precision.

Quantum Physics Mesoscale and Nanoscale Physics

Unique Sharp Local Minimum in $\ell_1$-minimization Complete Dictionary Learning

no code implementations22 Feb 2019 Yu Wang, Siqi Wu, Bin Yu

First, we obtain a necessary and sufficient norm condition for the reference dictionary $D^*$ to be a sharp local minimum of the expected $\ell_1$ objective function.

Dictionary Learning

DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators

no code implementations20 Feb 2019 Yu Xing, Shuang Liang, Lingzhi Sui, Xijie Jia, Jiantao Qiu, Xin Liu, Yushun Wang, Yu Wang, Yi Shan

On the Xilinx ZU2 @330 MHz and ZU9 @330 MHz, we achieve equivalently state-of-the-art performance on our benchmarks by na\"ive implementations without optimizations, and the throughput is further improved up to 1. 26x by leveraging heterogeneous optimizations in DNNVM.

A New Concept of Deep Reinforcement Learning based Augmented General Sequence Tagging System

no code implementations26 Dec 2018 Yu Wang, Abhishek Patel, Hongxia Jin

In this paper, a new deep reinforcement learning based augmented general sequence tagging system is proposed.

reinforcement-learning

A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling

1 code implementation NAACL 2018 Yu Wang, Yilin Shen, Hongxia Jin

The most effective algorithms are based on the structures of sequence to sequence models (or "encoder-decoder" models), and generate the intents and semantic tags either using separate models or a joint model.

Frame Intent Detection +3

Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks

no code implementations30 Oct 2018 Anton Ragni, Qiujia Li, Mark Gales, Yu Wang

These errors are not accounted for by the standard confidence estimation schemes and are hard to rectify in the upstream and downstream processing.

User Information Augmented Semantic Frame Parsing using Coarse-to-Fine Neural Networks

no code implementations18 Sep 2018 Yilin Shen, Xiangyu Zeng, Yu Wang, Hongxia Jin

The results show that our approach leverages such simple user information to outperform state-of-the-art approaches by 0. 25% for intent detection and 0. 31% for slot filling using standard training data.

Frame Intent Detection +3

Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems

2 code implementations29 Jul 2018 Xiujun Li, Yu Wang, Siqi Sun, Sarah Panda, Jingjing Liu, Jianfeng Gao

This proposal introduces a Dialogue Challenge for building end-to-end task-completion dialogue systems, with the goal of encouraging the dialogue research community to collaborate and benchmark on standard datasets and unified experimental environment.

Nonparametric Topic Modeling with Neural Inference

no code implementations18 Jun 2018 Xuefei Ning, Yin Zheng, Zhuxi Jiang, Yu Wang, Huazhong Yang, Junzhou Huang

Moreover, we also propose HiTM-VAE, where the document-specific topic distributions are generated in a hierarchical manner.

Topic Models

A Deeply-Recursive Convolutional Network for Crowd Counting

no code implementations15 May 2018 Xinghao Ding, Zhirui Lin, Fujin He, Yu Wang, Yue Huang

The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.

Crowd Counting

Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks

no code implementations14 May 2018 Wenshuo Li, Jincheng Yu, Xuefei Ning, Pengjun Wang, Qi Wei, Yu Wang, Huazhong Yang

So, in this paper, we propose a hardware-software collaborative attack framework to inject hidden neural network Trojans, which works as a back-door without requiring manipulating input images and is flexible for different scenarios.

Autonomous Driving Face Recognition +4

A Counter-Forensic Method for CNN-Based Camera Model Identification

no code implementations6 May 2018 David Güera, Yu Wang, Luca Bondi, Paolo Bestagini, Stefano Tubaro, Edward J. Delp

We examine in this paper the problem of identifying the camera model or type that was used to take an image and that can be spoofed.

Automated Big Traffic Analytics for Cyber Security

no code implementations24 Apr 2018 Yuantian Miao, Zichan Ruan, Lei Pan, Yu Wang, Jun Zhang, Yang Xiang

Network traffic analytics technology is a cornerstone for cyber security systems.

Cryptography and Security

PoTrojan: powerful neural-level trojan designs in deep learning models

no code implementations8 Feb 2018 Minhui Zou, Yang Shi, Chengliang Wang, Fangyu Li, WenZhan Song, Yu Wang

With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life.

Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription

no code implementations1 Feb 2018 Yu Wang, Xie Chen, Mark Gales, Anton Ragni, Jeremy Wong

As the combination approaches become more complicated the difference between the phonetic and graphemic systems further decreases.

Automatic Speech Recognition

A Bayesian Nonparametric Topic Model with Variational Auto-Encoders

no code implementations ICLR 2018 Xuefei Ning, Yin Zheng, Zhuxi Jiang, Yu Wang, Huazhong Yang, Junzhou Huang

On the other hand, different with the other BNP topic models, the inference of iTM-VAE is modeled by neural networks, which has rich representation capacity and can be computed in a simple feed-forward manner.

Representation Learning Topic Models

A Survey of FPGA Based Neural Network Accelerator

no code implementations24 Dec 2017 Kaiyuan Guo, Shulin Zeng, Jincheng Yu, Yu Wang, Huazhong Yang

Various FPGA based accelerator designs have been proposed with software and hardware optimization techniques to achieve high speed and energy efficiency.

Hardware Architecture

Deep Gradient Compression Reduce the Communication Bandwidth For distributed Traning

1 code implementation The International Conference on Learning Representations 2017 Yujun Lin, Song Han, Huizi Mao, Yu Wang, W. Dally

Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure.

Federated Learning Image Classification +1

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

2 code implementations ICLR 2018 Yujun Lin, Song Han, Huizi Mao, Yu Wang, William J. Dally

The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections.

Federated Learning Image Classification