Search Results for author: Yang Li

Found 203 papers, 50 papers with code

Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy

no code implementations EMNLP 2021 Dayu Li, Xiaodan Zhu, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

Emotion inference in multi-turn conversations aims to predict the participant’s emotion in the next upcoming turn without knowing the participant’s response yet, and is a necessary step for applications such as dialogue planning.

ACFlow: Flow Models for Arbitrary Conditional Likelihoods

1 code implementation ICML 2020 Yang Li, Shoaib Akbar, Junier Oliva

However, a majority of generative modeling approaches are focused solely on the joint distribution $p(x)$ and utilize models where it is intractable to obtain the conditional distribution of some arbitrary subset of features $x_u$ given the rest of the observed covariates $x_o$: $p(x_u \mid x_o)$.


Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale

1 code implementation18 Jan 2022 Yang Li, Yu Shen, Huaijun Jiang, Wentao Zhang, Jixiang Li, Ji Liu, Ce Zhang, Bin Cui

The ever-growing demand and complexity of machine learning are putting pressure on hyper-parameter tuning systems: while the evaluation cost of models continues to increase, the scalability of state-of-the-arts starts to become a crucial bottleneck.

Joint Planning of Distributed Generations and Energy Storage in Active Distribution Networks: A Bi-Level Programming Approach

no code implementations15 Jan 2022 Yang Li, Bo Feng, Bin Wang, Shuchao Sun

In this model, the upper-level aims to seek the optimal location and capacity of DGs and energy storage, while the lower-level optimizes the operation of energy storage devices.

Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale

no code implementations11 Jan 2022 Gang Li, Gilles Baechler, Manuel Tragut, Yang Li

The layout of a mobile screen is a critical data source for UI design research and semantic understanding of the screen.


Swin Transformer for Fast MRI

1 code implementation10 Jan 2022 Jiahao Huang, Yingying Fang, Yinzhe Wu, Huanjun Wu, Zhifan Gao, Yang Li, Javier Del Ser, Jun Xia, Guang Yang

The IM and OM were 2D convolutional layers and the FEM was composed of a cascaded of residual Swin transformer blocks (RSTBs) and 2D convolutional layers.

MRI Reconstruction

N-Omniglot: a Large-scale Neuromorphic Dataset for Spatio-Temporal Sparse Few-shot Learning

no code implementations25 Dec 2021 Yang Li, Yiting Dong, Dongcheng Zhao, Yi Zeng

Few-shot learning (learning with a few samples) is one of the most important capacities of the human brain.

Few-Shot Learning

A review of data-driven short-term voltage stability assessment of power systems: Concept, principle, and challenges

no code implementations22 Dec 2021 Jiting Cao, Meng Zhang, Yang Li

With the rapid growth of power market reform and power demand, the power transmission capacity of a power grid is approaching its limit, and the secure and stable operation of power systems becomes increasingly important.

Learning to Model the Relationship Between Brain Structural and Functional Connectomes

1 code implementation18 Dec 2021 Yang Li, Gonzalo Mateos, Zhengwu Zhang

Recent advances in neuroimaging along with algorithmic innovations in statistical learning from network data offer a unique pathway to integrate brain structure and function, and thus facilitate revealing some of the brain's organizing principles at the system level.

Graph Representation Learning

Homography Decomposition Networks for Planar Object Tracking

1 code implementation15 Dec 2021 Xinrui Zhan, Yueran Liu, Jianke Zhu, Yang Li

Planar object tracking plays an important role in AI applications, such as robotics, visual servoing, and visual SLAM.

Object Tracking

Progressive Graph Convolution Network for EEG Emotion Recognition

no code implementations14 Dec 2021 Yijin Zhou, Fu Li, Yang Li, Youshuo Ji, Guangming Shi, Wenming Zheng, Lijian Zhang, Yuanfang Chen, Rui Cheng

Moreover, motivated by the observation of the relationship between coarse- and fine-grained emotions, we adopt a dual-head module that enables the PGCN to progressively learn more discriminative EEG features, from coarse-grained (easy) to fine-grained categories (difficult), referring to the hierarchical characteristic of emotion.

EEG EEG Emotion Recognition

Hierarchical Stochastic Scheduling of Multi-Community Integrated Energy Systems in Uncertain Environments via Stackelberg Game

no code implementations14 Dec 2021 Yang Li, Bin Wang, Zhen Yang, Jiazheng Li, Chen Chen

An operating entity utilizing community-integrated energy systems with a large number of small-scale distributed energy sources can easily trade with existing distribution markets.

Dynamic Exploitation Gaussian Bare-Bones Bat Algorithm for Optimal Reactive Power Dispatch to Improve the Safety and Stability of Power System

no code implementations13 Dec 2021 Zhaoyang Qu, Yunchang Dong, Sylvère Mugemanyi, Tong Yu, Xiaoyong Bo, Huashun Li, Yang Li, François Xavier Rugema, Christophe Bananeza

DeGBBBA is an advanced variant of GBBBA in which a modified Gaussian distribution is introduced so as to allow the dynamic adaptation of exploitation and exploitation in the proposed algorithm.

Continuous Control

Automated assessment of disease severity of COVID-19 using artificial intelligence with synthetic chest CT

no code implementations11 Dec 2021 Mengqiu Liu, Ying Liu, Yidong Yang, Aiping Liu, Shana Li, Changbing Qu, Xiaohui Qiu, Yang Li, Weifu Lv, Peng Zhang, Jie Wen

Correlations between imaging findings and clinical lab tests suggested the value of this system as a potential tool to assess disease severity of COVID-19.

Data Augmentation Lesion Segmentation

VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling

no code implementations10 Dec 2021 Yang Li, Gang Li, Xin Zhou, Mostafa Dehghani, Alexey Gritsenko

Our model consists of a multimodal Transformer encoder that jointly encodes UI images and structures, and performs UI object detection when the UI structures are absent in the input.

Object Detection Question Answering +1

A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems

no code implementations5 Dec 2021 Yang Li, Meng Zhang, Chen Chen

Facing the difficulty of expensive and trivial data collection and annotation, how to make a deep learning-based short-term voltage stability assessment (STVSA) model work well on a small training dataset is a challenging and urgent problem.

Data Augmentation

Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks

no code implementations3 Dec 2021 Yang Li, Yuichi Tanaka

In this paper, we propose two methods to improve the performance of GCs: 1) Utilizing structural information in the feature space, and 2) exploiting the multi-hop information in one GC step.

Iterative Connecting Probability Estimation for Networks

no code implementations NeurIPS 2021 Yichen Qin, Linhan Yu, Yang Li

Starting at a random initial point or an existing estimate, our method iteratively updates the pairwise vertex distances, the sets of similar vertices, and connecting probabilities to improve the precision of the estimate.

Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation

no code implementations NeurIPS 2021 Yunan Liu, Shanshan Zhang, Yang Li, Jian Yang

In this setting, we embed an additional pair of “latent-latent” to reduce the domain gap between the source and different latent domains, allowing the model to adapt well on multiple target domains simultaneously.

Domain Adaptation Meta-Learning +1

Stochastic optimal scheduling of demand response-enabled microgrids with renewable generations: An analytical-heuristic approach

no code implementations24 Nov 2021 Yang Li, Kang Li, Zhen Yang, Yang Yu, Runnan Xu, Miaosen Yang

In order to solve this model, this research combines Jaya algorithm and interior point method (IPM) to develop a hybrid analysis-heuristic solution method called Jaya-IPM, where the lower- and upper- levels are respectively addressed by the IPM and the Jaya, and the scheduling scheme is obtained via iterations between the two levels.

Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules

no code implementations15 Nov 2021 Dongcheng Zhao, Yang Li, Yi Zeng, Jihang Wang, Qian Zhang

Our Spiking CapsNet fully combines the strengthens of SNN and CapsNet, and shows strong robustness to noise and affine transformation.

Affine Transformation

DSBERT:Unsupervised Dialogue Structure learning with BERT

no code implementations9 Nov 2021 Bingkun Chen, Shaobing Dai, Shenghua Zheng, Lei Liao, Yang Li

Unsupervised dialogue structure learning is an important and meaningful task in natural language processing.

Dialogue Generation

Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks

no code implementations2 Nov 2021 Xiang Huang, Hongsheng Liu, Beiji Shi, Zidong Wang, Kang Yang, Yang Li, Bingya Weng, Min Wang, Haotian Chu, Jing Zhou, Fan Yu, Bei Hua, Lei Chen, Bin Dong

In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a promising method for solving both forward and inverse PDE problems.

A critical review of data-driven transient stability assessment of power systems: principles, prospects and challenges

no code implementations1 Nov 2021 Shitu Zhang, Zhixun Zhu, Yang Li

Transient stability assessment (TSA) has always been a fundamental means for ensuring the secure and stable operation of power systems.

Automated Hyperparameter Optimization Challenge at CIKM 2021 AnalyticCup

1 code implementation31 Oct 2021 Huaijun Jiang, Yu Shen, Yang Li

In this paper, we describe our method for tackling the automated hyperparameter optimization challenge in QQ Browser 2021 AI Algorithm Competiton (ACM CIKM 2021 AnalyticCup Track 2).

Hyperparameter Optimization

Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings

no code implementations29 Oct 2021 Guanglin Niu, Yang Li, Chengguang Tang, Zhongkai Hu, Shibin Yang, Peng Li, Chengyu Wang, Hao Wang, Jian Sun

The multi-relational Knowledge Base Question Answering (KBQA) system performs multi-hop reasoning over the knowledge graph (KG) to achieve the answer.

Knowledge Base Question Answering Knowledge Graph Embedding +1

Data Driven based Dynamic Correction Prediction Model for NOx Emission of Coal Fired Boiler

no code implementations29 Oct 2021 Zhenhao Tang, Deyu Zhu, Yang Li

The real-time prediction of NOx emissions is of great significance for pollutant emission control and unit operation of coal-fired power plants.

Deep DIC: Deep Learning-Based Digital Image Correlation for End-to-End Displacement and Strain Measurement

no code implementations26 Oct 2021 Ru Yang, Yang Li, Danielle Zeng, Ping Guo

StrainNet predicts the strain field directly from the image input without relying on the displacement prediction, which significantly improves the strain prediction accuracy.

Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models

no code implementations14 Oct 2021 Forrest Huang, Gang Li, Xin Zhou, John F. Canny, Yang Li

The design process of user interfaces (UIs) often begins with articulating high-level design goals.

Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning

no code implementations30 Sep 2021 Fengrui Liu, Yang Li, Baitong Li, Jiaxin Li, Huiyang Xie

Then an automatically-generating transaction strategy is constructed building on PPO with LSTM as the basis to construct the policy.

Extracting stochastic dynamical systems with $α$-stable Lévy noise from data

no code implementations30 Sep 2021 Yang Li, Yubin Lu, Shengyuan Xu, Jinqiao Duan

Despite the wide applications of non-Gaussian fluctuations in numerous physical phenomena, the data-driven approaches to extract stochastic dynamical systems with (non-Gaussian) L\'evy noise are relatively few so far.

Transferability Estimation for Semantic Segmentation Task

no code implementations30 Sep 2021 Yang Tan, Yang Li, Shao-Lun Huang

Recent analytical transferability metrics are mainly designed for image classification problem, and currently there is no specific investigation for the transferability estimation of semantic segmentation task, which is an essential problem in autonomous driving, medical image analysis, etc.

Autonomous Driving Image Classification +2

Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision

no code implementations19 Sep 2021 Yang Li, Guodong Long, Tao Shen, Jing Jiang

It consists of (1) a pairwise type-enriched sentence encoding module injecting both context-free and -related backgrounds to alleviate sentence-level wrong labeling, and (2) a hierarchical type-sentence alignment module enriching a sentence with the triple fact's basic attributes to support long-tail relations.

Knowledge Graphs Relation Extraction +1

Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization

no code implementations8 Sep 2021 Jingge Wang, Yang Li, Liyan Xie, Yao Xie

Given multiple source domains, domain generalization aims at learning a universal model that performs well on any unseen but related target domain.

Domain Generalization

Non-intrusive load decomposition based on CNN-LSTM hybrid deep learning model

no code implementations2 Sep 2021 Xinxin Zhou, Jingru Feng, Yang Li

In this paper, the proposed decomposition method is compared with the existing traditional deep learning load decomposition method.

Extracting Stochastic Governing Laws by Nonlocal Kramers-Moyal Formulas

1 code implementation28 Aug 2021 Yubin Lu, Yang Li, Jinqiao Duan

In this work, we propose a data-driven approach to extract stochastic governing laws with both (Gaussian) Brownian motion and (non-Gaussian) L\'evy motion, from short bursts of simulation data.

Lightweight Self-Attentive Sequential Recommendation

no code implementations25 Aug 2021 Yang Li, Tong Chen, Peng-Fei Zhang, Hongzhi Yin

Modern deep neural networks (DNNs) have greatly facilitated the development of sequential recommender systems by achieving state-of-the-art recommendation performance on various sequential recommendation tasks.

Sequential Recommendation

Optimal Scheduling of Integrated Demand Response-Enabled Community Integrated Energy Systems in Uncertain Environments

no code implementations18 Aug 2021 Yang Li, Bin Wang, Zhen Yang, Jiazheng Li, Guoqing Li

The community integrated energy system (CIES) is an essential energy internet carrier that has recently been the focus of much attention.

A BCS-GDE Algorithm for Multi-objective Optimization of Combined Cooling, Heating and Power Model

no code implementations17 Aug 2021 Jiaze Sun, Jiahui Deng, Yang Li, Shuaiyin Ma, Nan Han

District energy systems can not only reduce energy consumption but also set energy supply dispatching schemes according to demand.

Decision Making

Optimal Scheduling of Isolated Microgrids Using Automated Reinforcement Learning-based Multi-period Forecasting

no code implementations15 Aug 2021 Yang Li, Ruinong Wang, Zhen Yang

In order to reduce the negative impact of the uncertainty of load and renewable energies outputs on microgrid operation, an optimal scheduling model is proposed for isolated microgrids by using automated reinforcement learning-based multi-period forecasting of renewable power generations and loads.

Large-Scale Modeling of Mobile User Click Behaviors Using Deep Learning

no code implementations11 Aug 2021 Xin Zhou, Yang Li

Modeling tap or click sequences of users on a mobile device can improve our understandings of interaction behavior and offers opportunities for UI optimization by recommending next element the user might want to click on.

HelpViz: Automatic Generation of Contextual Visual MobileTutorials from Text-Based Instructions

no code implementations7 Aug 2021 Mingyuan Zhong, Gang Li, Peggy Chi, Yang Li

We present HelpViz, a tool for generating contextual visual mobile tutorials from text-based instructions that are abundant on the web.

Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning

1 code implementation7 Aug 2021 Bryan Wang, Gang Li, Xin Zhou, Zhourong Chen, Tovi Grossman, Yang Li

Mobile User Interface Summarization generates succinct language descriptions of mobile screens for conveying important contents and functionalities of the screen, which can be useful for many language-based application scenarios.

Dynamic Prediction Model for NOx Emission of SCR System Based on Hybrid Data-driven Algorithms

no code implementations3 Aug 2021 Zhenhao Tang, Shikui Wang, Shengxian Cao, Yang Li, Tao Shen

Aiming at the problem that delay time is difficult to determine and prediction accuracy is low in building prediction model of SCR system, a dynamic modeling scheme based on a hybrid of multiple data-driven algorithms was proposed.

Time Series

Frequency support Scheme based on parametrized power curve for de-loaded Wind Turbine under various wind speed

no code implementations2 Aug 2021 Cheng Zhong, Yueming Lv, Huayi Li, Jikai Chen, Yang Li

However, for the existing frequency regulation scheme of wind turbines, the control gains in the auxiliary frequency controller are difficult to set because of the compromise of the frequency regulation performance and the stable operation of wind turbines, especially when the wind speed remains variable.

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

1 code implementation31 Jul 2021 Wentao Zhang, Zhi Yang, Yexin Wang, Yu Shen, Yang Li, Liang Wang, Bin Cui

Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets.

Active Learning Knowledge Graphs

ROD: Reception-aware Online Distillation for Sparse Graphs

1 code implementation25 Jul 2021 Wentao Zhang, Yuezihan Jiang, Yang Li, Zeang Sheng, Yu Shen, Xupeng Miao, Liang Wang, Zhi Yang, Bin Cui

Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs.

Graph Learning Knowledge Distillation +4

Extracting Governing Laws from Sample Path Data of Non-Gaussian Stochastic Dynamical Systems

no code implementations21 Jul 2021 Yang Li, Jinqiao Duan

Advances in data science are leading to new progresses in the analysis and understanding of complex dynamics for systems with experimental and observational data.

VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition

3 code implementations19 Jul 2021 Yang Li, Yu Shen, Wentao Zhang, Jiawei Jiang, Bolin Ding, Yaliang Li, Jingren Zhou, Zhi Yang, Wentao Wu, Ce Zhang, Bin Cui

End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning.

AutoML Feature Engineering +1

Markov Blanket Discovery using Minimum Message Length

no code implementations16 Jul 2021 Yang Li, Kevin B Korb, Lloyd Allison

Causal discovery automates the learning of causal Bayesian networks from data and has been of active interest from their beginning.

Causal Discovery

Coordinating Flexible Demand Response and Renewable Uncertainties for Scheduling of Community Integrated Energy Systems with an Electric Vehicle Charging Station: A Bi-level Approach

no code implementations16 Jul 2021 Yang Li, Meng Han, Zhen Yang, Guoqing Li

A community integrated energy system (CIES) with an electric vehicle charging station (EVCS) provides a new way for tackling growing concerns of energy efficiency and environmental pollution, it is a critical task to coordinate flexible demand response and multiple renewable uncertainties.

Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach

no code implementations16 Jul 2021 Yang Li, Jiazheng Li, Yi Wang

Scenario generation is a fundamental and crucial tool for decision-making in power systems with high-penetration renewables.

Decision Making Federated Learning

Dynamic State Estimation for Integrated Natural Gas and Electric Power Systems

no code implementations13 Jul 2021 Liang Chen, Xinxin Hui, Songlin Gu, Manyun Huang, Yang Li

Boundary conditions of pipeline networks are used as supplementary constraints in the system model.

Towards Robust Active Feature Acquisition

no code implementations9 Jul 2021 Yang Li, Siyuan Shan, Qin Liu, Junier B. Oliva

Our framework can easily handle a large number of features using a hierarchical acquisition policy and is more robust to OOD inputs with the help of an OOD detector for partially observed data.

Attribute-aware Explainable Complementary Clothing Recommendation

no code implementations4 Jul 2021 Yang Li, Tong Chen, Zi Huang

As a result, this creates a severe bottleneck when we are trying to advance the recommendation accuracy and generating fine-grained explanations since the explicit attributes have only loose connections to the actual recommendation process.

Recommendation Systems

Virtual synchronous generator of PV generation without energy storage for frequency support in autonomous microgrid

no code implementations4 Jul 2021 Cheng Zhong, Huayi Li, Yang Zhou, Yueming Lv, Jikai Chen, Yang Li

PV generation reserve a part of the active power in accordance with the pre-defined power versus voltage curve.

Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling

1 code implementation30 Jun 2021 Yang Li, Shihao Ji

We term our algorithm Dep-$L_0$ as it prunes networks via a dependency-enabled $L_0$ regularization.

Network Pruning Variational Inference

Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentation

no code implementations30 Jun 2021 Yang Li, Tong Chen, Hongzhi Yin, Zi Huang

Furthermore, the sparse POI-POI transitions restrict the ability of a model to learn effective sequential patterns for recommendation.

Multi-Task Learning

Context-Aware Attention-Based Data Augmentation for POI Recommendation

no code implementations30 Jun 2021 Yang Li, Yadan Luo, Zheng Zhang, Shazia W. Sadiq, Peng Cui

It aims at suggesting the next POI to a user in spatial and temporal context, which is a practical yet challenging task in various applications.

Data Augmentation

Graph Routing between Capsules

no code implementations22 Jun 2021 Yang Li, Wei Zhao, Erik Cambria, Suhang Wang, Steffen Eger

Therefore, in this paper, we introduce a new capsule network with graph routing to learn both relationships, where capsules in each layer are treated as the nodes of a graph.

Text Classification

Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning

no code implementations CVPR 2021 Shichao Kan, Yigang Cen, Yang Li, Vladimir Mladenovic, Zhihai He

During training, this relative order prediction network and the feature embedding network are tightly coupled, providing mutual constraints to each other to improve overall metric learning performance in a cooperative manner.

Image Retrieval Metric Learning

Spatial Assembly Networks for Image Representation Learning

no code implementations CVPR 2021 Yang Li, Shichao Kan, Jianhe Yuan, Wenming Cao, Zhihai He

It has been long recognized that deep neural networks are sensitive to changes in spatial configurations or scene structures.

Image Classification Image Retrieval +2

Practical Transferability Estimation for Image Classification Tasks

no code implementations19 Jun 2021 Yang Tan, Yang Li, Shao-Lun Huang

Transferability estimation is an essential problem in transfer learning to predict how good the performance is when transferring a source model (or source task) to a target task.

Image Classification Model Selection +1

Rethinking Training from Scratch for Object Detection

1 code implementation6 Jun 2021 Yang Li, Hong Zhang, Yu Zhang

The ImageNet pre-training initialization is the de-facto standard for object detection.

Object Detection

IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse

no code implementations1 Jun 2021 Liangliang Shi, Yang Li, Junchi Yan

Based on this observation, we propose a necessary condition of IID generation and provide a new loss to encourage the closeness between the inverse source of real data and the Gaussian source in the latent space to regularize the generation to be IID from the target distribution.

OpenBox: A Generalized Black-box Optimization Service

6 code implementations1 Jun 2021 Yang Li, Yu Shen, Wentao Zhang, Yuanwei Chen, Huaijun Jiang, Mingchao Liu, Jiawei Jiang, Jinyang Gao, Wentao Wu, Zhi Yang, Ce Zhang, Bin Cui

Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, engineering, physics, and experimental design.

Experimental Design Transfer Learning

BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons

no code implementations27 May 2021 Dongcheng Zhao, Yi Zeng, Yang Li

With the combination of the two mechanisms, we propose a deep spiking neural network with adaptive self-feedback and balanced excitatory and inhibitory neurons (BackEISNN).

BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons

no code implementations27 May 2021 Yang Li, Yi Zeng, Dongcheng Zhao

Also, when ResNet structure-based ANNs are converted, the information of output neurons is incomplete due to the rapid transmission of the shortcut path.

Joint Text and Label Generation for Spoken Language Understanding

no code implementations11 May 2021 Yang Li, Ben Athiwaratkun, Cicero Nogueira dos santos, Bing Xiang

In this work, we propose to leverage the prior information embedded in pretrained language models (LM) to improve generalization for intent classification and slot labeling tasks with limited training data.

Intent Classification Learning with noisy labels +1

4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface

1 code implementation ICCV 2021 Yang Li, Hikari Takehara, Takafumi Taketomi, Bo Zheng, Matthias Nießner

Tracking non-rigidly deforming scenes using range sensors has numerous applications including computer vision, AR/VR, and robotics.

Motion Estimation

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion

1 code implementation27 Apr 2021 Guanglin Niu, Yang Li, Chengguang Tang, Ruiying Geng, Jian Dai, Qiao Liu, Hao Wang, Jian Sun, Fei Huang, Luo Si

Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances.

Few-Shot Learning Knowledge Graph Completion +1

GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing

no code implementations20 Apr 2021 Wentao Zhang, Yu Shen, Zheyu Lin, Yang Li, Xiaosen Li, Wen Ouyang, Yangyu Tao, Zhi Yang, Bin Cui

In recent studies, neural message passing has proved to be an effective way to design graph neural networks (GNNs), which have achieved state-of-the-art performance in many graph-based tasks.

GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention

no code implementations13 Apr 2021 Yang Li, Di Wang, José M. F. Moura

This task is challenging as models need not only to capture spatial dependency and temporal dependency within the data, but also to leverage useful auxiliary information for accurate predictions.

OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations

1 code implementation CVPR 2021 Yang Tan, Yang Li, Shao-Lun Huang

Specifically, we use optimal transport to estimate domain difference and the optimal coupling between source and target distributions, which is then used to derive the conditional entropy of the target task (task difference).

Model Selection Transfer Learning

Optimal Scheduling of Integrated Demand Response-Enabled Integrated Energy Systems with Uncertain Renewable Generations: A Stackelberg Game Approach

no code implementations8 Mar 2021 Yang Li, Chunling Wang, Guoqing Li, Chen Chen

In order to balance the interests of integrated energy operator (IEO) and users, a novel Stackelberg game-based optimization framework is proposed for the optimal scheduling of integrated demand response (IDR)-enabled integrated energy systems with uncertain renewable generations, where the IEO acts as the leader who pursues the maximization of his profits by setting energy prices, while the users are the follower who adjusts energy consumption plans to minimize their energy costs.

Coordinated Cyber-Attack Detection Model of Cyber-Physical Power System Based on the Operating State Data Link

no code implementations27 Feb 2021 Lei Wang, Pengcheng Xu, Zhaoyang Qu, Xiaoyong Bo, Yunchang Dong, Zhenming Zhang, Yang Li

Existing coordinated cyber-attack detection methods have low detection accuracy and efficiency and poor generalization ability due to difficulties dealing with unbalanced attack data samples, high data dimensionality, and noisy data sets.

Cyber Attack Detection

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

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

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

Relaxed phase-matching constraints in zero-index waveguides

no code implementations25 Feb 2021 Justin R. Gagnon, Orad Reshef, Daniel H. G. Espinosa, M. Zahirul Alam, Daryl I. Vulis, Erik N. Knall, Jeremy Upham, Yang Li, Ksenia Dolgaleva, Eric Mazur, Robert W. Boyd

However, the utility of all such parametric nonlinear optical processes is hampered by phase-matching requirements.

Optics Applied Physics

Distinct thermodynamic and dynamic effects produced by scale factors in conformally related Einstein-power-Yang-Mills black holes

no code implementations24 Feb 2021 Yang Li, Yan-Gang Miao

We find that the thermodynamics of this class of conformally related black holes is independent of scale factors.

General Relativity and Quantum Cosmology High Energy Physics - Theory

TapNet: The Design, Training, Implementation, and Applications of a Multi-Task Learning CNN for Off-Screen Mobile Input

no code implementations18 Feb 2021 Michael Xuelin Huang, Yang Li, Nazneen Nazneen, Alexander Chao, Shumin Zhai

To make off-screen interaction without specialized hardware practical, we investigate using deep learning methods to process the common built-in IMU sensor (accelerometers and gyroscopes) on mobile phones into a useful set of one-handed interaction events.

Multi-Task Learning

Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement and Crowd Genetic Programming

no code implementations17 Feb 2021 Mingyuan Zhong, Gang Li, Yang Li

Based on our experiments, Spacewalker allows designers to effectively search a large design space of a UI, using the language they are familiar with, and improve their design rapidly at a minimal cost.

Partially Observed Exchangeable Modeling

no code implementations11 Feb 2021 Yang Li, Junier B. Oliva

Modeling dependencies among features is fundamental for many machine learning tasks.


NRTSI: Non-Recurrent Time Series Imputation

1 code implementation5 Feb 2021 Siyuan Shan, Yang Li, Junier B. Oliva

Time series imputation is a fundamental task for understanding time series with missing data.

Imputation Time Series

Deep Learning for Short-Term Voltage Stability Assessment of Power Systems

no code implementations4 Feb 2021 Meng Zhang, Jiazheng Li, Yang Li, Runnan Xu

Secondly, a long short-term memory (LSTM) based assessment model is built through learning the time dependencies from the post-disturbance system dynamics.

Modeling Method for the Coupling Relations of Microgrid Cyber-Physical Systems Driven by Hybrid Spatiotemporal Events

no code implementations1 Feb 2021 Xiaoyong Bo, Xiaoyu Chen, Huashun Li, Yunchang Dong, Zhaoyang Qu, Lei Wang, Yang Li

Considering the constraints of the temporal conversion of information flow and energy flow, a microgrid CPS coupling model is established, the effectiveness of which is verified by simulating false data injection attack (FDIA) scenarios.

Decision Making

Multitask Learning for Emotion and Personality Detection

1 code implementation7 Jan 2021 Yang Li, Amirmohammad Kazameini, Yash Mehta, Erik Cambria

In recent years, deep learning-based automated personality trait detection has received a lot of attention, especially now, due to the massive digital footprints of an individual.

Language Modelling

InvertGAN: Reducing mode collapse with multi-dimensional Gaussian Inversion

no code implementations1 Jan 2021 Liangliang Shi, Yang Li, Junchi Yan

Generative adversarial networks have shown their ability in capturing high-dimensional complex distributions and generating realistic data samples e. g. images.

Efficient Automatic CASH via Rising Bandits

no code implementations8 Dec 2020 Yang Li, Jiawei Jiang, Jinyang Gao, Yingxia Shao, Ce Zhang, Bin Cui

In this framework, the BO methods are used to solve the HPO problem for each ML algorithm separately, incorporating a much smaller hyperparameter space for BO methods.

Hyperparameter Optimization Multi-Armed Bandits

MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements

6 code implementations5 Dec 2020 Yang Li, Yu Shen, Jiawei Jiang, Jinyang Gao, Ce Zhang, Bin Cui

Instead of sampling configurations randomly in HB, BOHB samples configurations based on a BO surrogate model, which is constructed with the high-fidelity measurements only.

Hyperparameter Optimization

Interpretable Models in ANNs

no code implementations24 Nov 2020 Yang Li

Artificial neural networks are often very complex and too deep for a human to understand.

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention

2 code implementations COLING 2020 Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

Then, facilitated by the proposed base model, we introduce collaborating relation features shared among relations in the hierarchies to promote the relation-augmenting process and balance the training data for long-tail relations.

Relation Extraction

Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements

1 code implementation EMNLP 2020 Yang Li, Gang Li, Luheng He, Jingjie Zheng, Hong Li, Zhiwei Guan

We propose widget captioning, a novel task for automatically generating language descriptions for UI elements from multimodal input including both the image and the structural representations of user interfaces.

Active Feature Acquisition with Generative Surrogate Models

no code implementations6 Oct 2020 Yang Li, Junier B. Oliva

Many real-world situations allow for the acquisition of additional relevant information when making an assessment with limited or uncertain data.

A Machine Learning Framework for Computing the Most Probable Paths of Stochastic Dynamical Systems

no code implementations1 Oct 2020 Yang Li, Jinqiao Duan, Xianbin Liu

The emergence of transition phenomena between metastable states induced by noise plays a fundamental role in a broad range of nonlinear systems.

A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition

no code implementations21 Sep 2020 Yang Li, Boxun Fu, Fu Li, Guangming Shi, Wenming Zheng

So it is necessary to give more attention to the EEG samples with strong transferability rather than forcefully training a classification model by all the samples.

EEG EEG Emotion Recognition

Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss

no code implementations ECCV 2020 Yang Li, Shichao Kan, Zhihai He

To further enhance the inter-class discriminative power of the feature generated by this network, we adapt the concept of triplet loss from supervised metric learning to our unsupervised case and introduce the contrastive clustering loss.

Metric Learning

Exchangeable Neural ODE for Set Modeling

no code implementations NeurIPS 2020 Yang Li, Haidong Yi, Christopher M. Bender, Siyuan Shan, Junier B. Oliva

Reasoning over an instance composed of a set of vectors, like a point cloud, requires that one accounts for intra-set dependent features among elements.

A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges

no code implementations26 Jul 2020 Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun

Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases.

Information Retrieval Question Answering +1

A Novel Ensemble Deep Learning Model for Stock Prediction Based on Stock Prices and News

no code implementations23 Jul 2020 Yang Li, Yi Pan

This paper proposes to use sentiment analysis to extract useful information from multiple textual data sources and a blending ensemble deep learning model to predict future stock movement.

Sentiment Analysis Stock Prediction +1

Multi-Stage Influence Function

no code implementations NeurIPS 2020 Hongge Chen, Si Si, Yang Li, Ciprian Chelba, Sanjiv Kumar, Duane Boning, Cho-Jui Hsieh

With this score, we can identify the pretraining examples in the pretraining task that contribute most to a prediction in the finetuning task.

Transfer Learning

RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Model

no code implementations15 Jul 2020 Ziyue Zhang, Shuai Jiang, Congzhentao Huang, Yang Li, Richard Yi Da Xu

To solve this challenge, we proposed a Teacher-Student GAN model (TS-GAN) to adopt different domains and guide the ReID backbone to learn better ReID information.

Person Re-Identification

SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes

no code implementations4 Jul 2020 Yang Li, Tianwei Zhang, Yoshihiko Nakamura, Tatsuya Harada

We present SplitFusion, a novel dense RGB-D SLAM framework that simultaneously performs tracking and dense reconstruction for both rigid and non-rigid components of the scene.

Probabilistic Classification Vector Machine for Multi-Class Classification

no code implementations29 Jun 2020 Shengfei Lyu, Xing Tian, Yang Li, Bingbing Jiang, Huanhuan Chen

The probabilistic classification vector machine (PCVM) synthesizes the advantages of both the support vector machine and the relevant vector machine, delivering a sparse Bayesian solution to classification problems.

General Classification Multi-class Classification

Attention-based Graph ResNet for Motor Intent Detection from Raw EEG signals

1 code implementation25 Jun 2020 Shuyue Jia, Yimin Hou, Yan Shi, Yang Li

In previous studies, decoding electroencephalography (EEG) signals has not considered the topological relationship of EEG electrodes.

EEG Intent Detection +1

Dynamic Feature Acquisition with Arbitrary Conditional Flows

no code implementations13 Jun 2020 Yang Li, Junier B. Oliva

To trade off the improvement with the cost of acquisition, we leverage an information theoretic metric, conditional mutual information, to select the most informative feature to acquire.

Grafted network for person re-identification

no code implementations2 Jun 2020 Jiabao Wang, Yang Li, Shanshan Jiao, Zhuang Miao, Rui Zhang

In order to relieve this problem, we propose a novel grafted network (GraftedNet), which is designed by grafting a high-accuracy rootstock and a light-weighted scion.

Person Re-Identification

A heterogeneous branch and multi-level classification network for person re-identification

no code implementations2 Jun 2020 Jiabao Wang, Yang Li, Yangshuo Zhang, Zhuang Miao, Rui Zhang

A new heterogeneous branch, SE-Res-Branch, is proposed based on the SE-Res module, which consists of the Squeeze-and-Excitation block and the residual block.

General Classification Person Re-Identification

A Data-Driven Approach for Discovering Stochastic Dynamical Systems with Non-Gaussian Levy Noise

no code implementations7 May 2020 Yang Li, Jinqiao Duan

We then design a numerical algorithm to compute the drift, diffusion coefficient and jump measure, and thus extract a governing stochastic differential equation with Gaussian and non-Gaussian noise.

Mapping Natural Language Instructions to Mobile UI Action Sequences

2 code implementations ACL 2020 Yang Li, Jiacong He, Xin Zhou, Yuan Zhang, Jason Baldridge

We present a new problem: grounding natural language instructions to mobile user interface actions, and create three new datasets for it.

SSIM-Based CTU-Level Joint Optimal Bit Allocation and Rate Distortion Optimization

no code implementations28 Apr 2020 Yang Li, Xuanqin Mou

This problem is due to the lack of an accurate R-$D_\text{SSIM}$ model that can be used uniformly in both OBA and RDO.


Anomalous Motion of Particle Levitated by Laguerre-Gaussian beam

no code implementations14 Apr 2020 Yang Li, Lei-Ming Zhou, Nan Zhao

We calculated the scattering force distribution of a micro-particle trapped in an optical tweezers formed by the strongly focused LG beam, and showed that there exist stable trajectories of the particle that controlled by the negative torque.


Learning to Optimize Non-Rigid Tracking

no code implementations CVPR 2020 Yang Li, Aljaž Božič, Tianwei Zhang, Yanli Ji, Tatsuya Harada, Matthias Nießner

One of the widespread solutions for non-rigid tracking has a nested-loop structure: with Gauss-Newton to minimize a tracking objective in the outer loop, and Preconditioned Conjugate Gradient (PCG) to solve a sparse linear system in the inner loop.

Defense Through Diverse Directions

no code implementations ICML 2020 Christopher M. Bender, Yang Li, Yifeng Shi, Michael K. Reiter, Junier B. Oliva

In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training.

Adversarial Robustness

FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow

no code implementations11 Mar 2020 Tianwei Zhang, Huayan Zhang, Yang Li, Yoshihiko Nakamura, Lei Zhang

Dynamic environments are challenging for visual SLAM since the moving objects occlude the static environment features and lead to wrong camera motion estimation.

Motion Estimation Optical Flow Estimation

Differential Evolution with Individuals Redistribution for Real Parameter Single Objective Optimization

no code implementations1 Mar 2020 Cheng-Jun Li, Yang Li

Versions of the ten DE algorithms based on individuals redistribution are compared with not only original version but also version based on complete restart, where individuals redistribution and complete restart are based on the same entry criterion.

Deep Learning-based End-to-end Diagnosis System for Avascular Necrosis of Femoral Head

no code implementations12 Feb 2020 Yang Li, Yan Li, Hua Tian

To the best of our knowledge, this study is the first research on the prospective use of a deep learning-based diagnosis system for AVNFH by conducting two pilot studies representing real-world application scenarios.

Decision Making Head Detection

Illumination adaptive person reid based on teacher-student model and adversarial training

no code implementations5 Feb 2020 Ziyue Zhang, Richard YD Xu, Shuai Jiang, Yang Li, Congzhentao Huang, Chen Deng

Most existing works in Person Re-identification (ReID) focus on settings where illumination either is kept the same or has very little fluctuation.

General Classification Person Re-Identification

Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders

no code implementations14 Jan 2020 Yang Li, Julien Amelot, Xin Zhou, Samy Bengio, Si Si

While we focus on interface layout prediction, our model can be generally applicable for other layout prediction problems that involve tree structures and 2-dimensional placements.

Attribute-aware Pedestrian Detection in a Crowd

1 code implementation21 Oct 2019 Jialiang Zhang, Lixiang Lin, Yang Li, Yun-chen Chen, Jianke Zhu, Yao Hu, Steven C. H. Hoi

To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion.

Pedestrian Detection


1 code implementation NeurIPS 2020 Siyuan Shan, Yang Li, Junier Oliva

Making an adaptive prediction based on one's input is an important ability for general artificial intelligence.

Meta-Learning Multi-Task Learning

Flow Models for Arbitrary Conditional Likelihoods

1 code implementation13 Sep 2019 Yang Li, Shoaib Akbar, Junier B. Oliva

Understanding the dependencies among features of a dataset is at the core of most unsupervised learning tasks.

Image Inpainting Imputation

Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data

no code implementations9 Sep 2019 Yang Li, José M. F. Moura

Specifically, we start by learning the structure of the graph that parsimoniously represents the spatial dependency between the data at different locations.

What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning

no code implementations4 Sep 2019 Yang Li, Thomas Strohmer

We propose a hybrid hardware-software framework that has the potential to significantly reduce the computational complexity and memory requirements of on-device machine learning.

Compressive Sensing Image Classification

Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets

no code implementations4 Sep 2019 Yang Li, Jianhe Yuan, Zhiqun Zhao, Hao Sun, Zhihai He

In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets.

Neural Plasticity Networks

1 code implementation13 Aug 2019 Yang Li, Shihao Ji

To the best of our knowledge, this is the first learning framework that unifies network sparsification and network expansion in an end-to-end training pipeline.

Image Classification

Inferring Latent dimension of Linear Dynamical System with Minimum Description Length

no code implementations23 Jun 2019 Yang Li

This paper addresses the issue and proposes a criterion for linear dynamical system based on the principle of minimum description length.

Model Selection

Bayesian Optimization with Directionally Constrained Search

no code implementations22 Jun 2019 Yang Li, Yaqiang Yao

This constraint demands an optimizer to be aware of its remaining budget and able to spend it wisely, in order to return as better a point as possible.

Robustness Verification of Tree-based Models

2 code implementations NeurIPS 2019 Hongge Chen, huan zhang, Si Si, Yang Li, Duane Boning, Cho-Jui Hsieh

We show that there is a simple linear time algorithm for verifying a single tree, and for tree ensembles, the verification problem can be cast as a max-clique problem on a multi-partite graph with bounded boxicity.

Event Detection without Triggers

no code implementations NAACL 2019 Shulin Liu, Yang Li, Feng Zhang, Tao Yang, Xinpeng Zhou

The goal of event detection (ED) is to detect the occurrences of events and categorize them.

Event Detection

Saliency detection based on structural dissimilarity induced by image quality assessment model

1 code implementation24 May 2019 Yang Li, Xuanqin Mou

Similar to IQA models, the structural dissimilarity is computed based on the correlation of the structural features.

Image Quality Assessment Saliency Detection

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

4 code implementations KDD 2019 Wei-Lin Chiang, Xuanqing Liu, Si Si, Yang Li, Samy Bengio, Cho-Jui Hsieh

Furthermore, Cluster-GCN allows us to train much deeper GCN without much time and memory overhead, which leads to improved prediction accuracy---using a 5-layer Cluster-GCN, we achieve state-of-the-art test F1 score 99. 36 on the PPI dataset, while the previous best result was 98. 71 by [16].

Graph Clustering Graph Convolutional Network +2

Integrating Tensor Similarity to Enhance Clustering Performance

no code implementations10 May 2019 Hong Peng, Yu Hu, Jiazhou Chen, Hai-Yan Wang, Yang Li, Hongmin Cai

The performance of most the clustering methods hinges on the used pairwise affinity, which is usually denoted by a similarity matrix.

An Information-Theoretic Metric of Transferability for Task Transfer Learning

1 code implementation ICLR 2019 Yajie Bao, Yang Li, Shao-Lun Huang, Lin Zhang, Amir R. Zamir, Leonidas J. Guibas

An important question in task transfer learning is to determine task transferability, i. e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task.

General Classification Scene Understanding +1

$L_0$-ARM: Network Sparsification via Stochastic Binary Optimization

1 code implementation9 Apr 2019 Yang Li, Shihao Ji

Thanks to the flexibility of ARM, many smooth or non-smooth parametric functions, such as scaled sigmoid or hard sigmoid, can be used to parameterize this binary optimization problem and the unbiasness of the ARM estimator is retained, while the hard concrete estimator has to rely on the hard sigmoid function to achieve conditional computation and thus accelerated training.

Accurate and Fast reconstruction of Porous Media from Extremely Limited Information Using Conditional Generative Adversarial Network

no code implementations4 Apr 2019 Junxi Feng, Xiaohai He, Qizhi Teng, Chao Ren, Honggang Chen, Yang Li

To overcome this shortcoming, in this study we proposed a deep learning-based framework for reconstructing full image from its much smaller sub-area(s).

Image Reconstruction

SADIH: Semantic-Aware DIscrete Hashing

no code implementations3 Apr 2019 Zheng Zhang, Guo-Sen Xie, Yang Li, Sheng Li, Zi Huang

Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications.

Pose Graph Optimization for Unsupervised Monocular Visual Odometry

no code implementations15 Mar 2019 Yang Li, Yoshitaka Ushiku, Tatsuya Harada

In this paper, we propose to leverage graph optimization and loop closure detection to overcome limitations of unsupervised learning based monocular visual odometry.

Loop Closure Detection Monocular Visual Odometry

Proving the NP-completeness of optimal moral graph triangulation

no code implementations6 Mar 2019 Yang Li, Lloyd Allison, Kevin Korb

Moral graphs were introduced in the 1980s as an intermediate step when transforming a Bayesian network to a junction tree, on which exact belief propagation can be efficiently done.

The Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality

1 code implementation5 Mar 2019 Yang Li, Kevin Korb, Lloyd Allison

A family of Markov blankets in a faithful Bayesian network satisfies the symmetry and consistency properties.

Exchangeable Generative Models with Flow Scans

1 code implementation5 Feb 2019 Christopher Bender, Kevin O'Connor, Yang Li, Juan Jose Garcia, Manzil Zaheer, Junier Oliva

In this work, we develop a new approach to generative density estimation for exchangeable, non-i. i. d.

Density Estimation

A Forest from the Trees: Generation through Neighborhoods

no code implementations4 Feb 2019 Yang Li, Tianxiang Gao, Junier B. Oliva

In this work, we propose to learn a generative model using both learned features (through a latent space) and memories (through neighbors).

Robust Deep Multi-Modal Sensor Fusion using Fusion Weight Regularization and Target Learning

no code implementations29 Jan 2019 Myung Seok Shim, Chenye Zhao, Yang Li, Xuchong Zhang, Wenrui Zhang, Peng Li

Sensor fusion has wide applications in many domains including health care and autonomous systems.

Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learning

no code implementations23 Jan 2019 Haiyun Peng, Yukun Ma, Soujanya Poria, Yang Li, Erik Cambria

Furthermore, we also fuse phonetic features with textual and visual features in order to mimic the way humans read and understand Chinese text.

Chinese Sentiment Analysis Sentiment Analysis

Ensemble Feature for Person Re-Identification

no code implementations17 Jan 2019 Jiabao Wang, Yang Li, Zhuang Miao

However, deep feature extracted by a single CNN network is not robust enough in testing stage.

Person Re-Identification

Face Recognition System

no code implementations8 Jan 2019 Yang Li, Sangwhan Cha

Deep learning is one of the new and important branches in machine learning.

Face Recognition

You Look Twice: GaterNet for Dynamic Filter Selection in CNNs

no code implementations CVPR 2019 Zhourong Chen, Yang Li, Samy Bengio, Si Si

The concept of conditional computation for deep nets has been proposed previously to improve model performance by selectively using only parts of the model conditioned on the sample it is processing.

Implementation of Robust Face Recognition System Using Live Video Feed Based on CNN

no code implementations18 Nov 2018 Yang Li, Sangwhan Cha

In this way, the advantages of multiple models can be combined to mention the recognition accuracy.

Face Recognition Iris Recognition +1

An amplitudes-perturbation data augmentation method in convolutional neural networks for EEG decoding

no code implementations6 Nov 2018 Xian-Rui Zhang, Meng-Ying Lei, Yang Li

Brain-Computer Interface (BCI) system provides a pathway between humans and the outside world by analyzing brain signals which contain potential neural information.

Data Augmentation EEG +1

Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks

no code implementations ICLR 2019 Patrick H. Chen, Si Si, Sanjiv Kumar, Yang Li, Cho-Jui Hsieh

The algorithm achieves an order of magnitude faster inference than the original softmax layer for predicting top-$k$ words in various tasks such as beam search in machine translation or next words prediction.

Machine Translation Translation

Area Attention

1 code implementation ICLR 2019 Yang Li, Lukasz Kaiser, Samy Bengio, Si Si

We propose area attention: a way to attend to areas in the memory, where each area contains a group of items that are structurally adjacent, e. g., spatially for a 2D memory such as images, or temporally for a 1D memory such as natural language sentences.

Image Captioning Machine Translation +1

Boosted Convolutional Neural Networks for Motor Imagery EEG Decoding with Multiwavelet-based Time-Frequency Conditional Granger Causality Analysis

no code implementations22 Oct 2018 Yang Li, Meng-Ying Lei, Xianrui Zhang, Weigang Cui, Yuzhu Guo, Ting-Wen Huang, Hua-Liang Wei

Decoding EEG signals of different mental states is a challenging task for brain-computer interfaces (BCIs) due to nonstationarity of perceptual decision processes.

EEG Eeg Decoding

Look Deeper See Richer: Depth-aware Image Paragraph Captioning

no code implementations ACM International Conference on Multimedia 2018 Ziwei Wang, Yadan Luo, Yang Li, Zi Huang, Hongzhi Yin

Existing image paragraph captioning methods give a series of sentences to represent the objects and regions of interests, where the descriptions are essentially generated by feeding the image fragments containing objects and regions into conventional image single-sentence captioning models.

Image Captioning Image Paragraph Captioning

Collaborative Learning for Extremely Low Bit Asymmetric Hashing

1 code implementation25 Sep 2018 Yadan Luo, Zi Huang, Yang Li, Fumin Shen, Yang Yang, Peng Cui

Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression.

Image Retrieval

Guess Me if You Can: Acronym Disambiguation for Enterprises

no code implementations ACL 2018 Yang Li, Bo Zhao, Ariel Fuxman, Fangbo Tao

The framework takes the enterprise corpus as input and produces a high-quality acronym disambiguation system as output.

Question Answering

Improved Techniques for Learning to Dehaze and Beyond: A Collective Study

1 code implementation30 Jun 2018 Yu Liu, Guanlong Zhao, Boyuan Gong, Yang Li, Ritu Raj, Niraj Goel, Satya Kesav, Sandeep Gottimukkala, Zhangyang Wang, Wenqi Ren, DaCheng Tao

Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e. g., object detection) of hazy images.

Image Dehazing Image Restoration +2

GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking

no code implementations NeurIPS 2018 Patrick H. Chen, Si Si, Yang Li, Ciprian Chelba, Cho-Jui Hsieh

Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses.

Language Modelling Model Compression +1

Progressive Neural Networks for Image Classification

no code implementations25 Apr 2018 Zhi Zhang, Guanghan Ning, Yigang Cen, Yang Li, Zhiqun Zhao, Hao Sun, Zhihai He

The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images.

General Classification Image Classification

Tensor graph convolutional neural network

no code implementations27 Mar 2018 Tong Zhang, Wenming Zheng, Zhen Cui, Yang Li

For cross graph convolution, a parameterized Kronecker sum operation is proposed to generate a conjunctive adjacency matrix characterizing the relationship between every pair of nodes across two subgraphs.

Matrix Completion