Search Results for author: Hao Wang

Found 288 papers, 84 papers with code

Toward Knowledge-Enriched Conversational Recommendation Systems

no code implementations NLP4ConvAI (ACL) 2022 Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.

Knowledge Graphs Recommendation Systems +1

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

1 code implementation ECCV 2020 Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li

However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.

3D Face Reconstruction

融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition)

no code implementations CCL 2021 Hao Wang, Junhui Li, ZhengXian Gong

“在汉语等其他有省略代词习惯的语言中, 通常会删掉可从上下文信息推断出的代词。尽管以Transformer为代表的的神经机器翻译模型取得了巨大的成功, 但这种省略现象依旧对神经机器翻译模型造成了很大的挑战。本文在Transformer基础上提出了一个融合零指代识别的翻译模型, 并引入篇章上下文来丰富指代信息。具体地, 该模型采用联合学习的框架, 在翻译模型基础上, 联合了一个分类任务, 即判别句子中省略代词在句子所表示的成分, 使得模型能够融合零指代信息辅助翻译。通过在中英对话数据集上的实验, 验证了本文提出方法的有效性, 与基准模型相比, 翻译性能提升了1. 48个BLEU值。”

Machine Translation

Theoretically Accurate Regularization Technique for Matrix Factorization based Recommender Systems

no code implementations21 May 2022 Hao Wang

Regularization is a popular technique to solve the overfitting problem of machine learning algorithms.

Fairness Recommendation Systems

Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization

no code implementations11 May 2022 Hao Wang, Kaifeng Yang, Michael Affenzeller, Michael Emmerich

This work provides the exact expression of the probability distribution of the hypervolume improvement (HVI) for bi-objective generalization of Bayesian optimization.

High Dimensional Bayesian Optimization with Kernel Principal Component Analysis

no code implementations28 Apr 2022 Kirill Antonov, Elena Raponi, Hao Wang, Carola Doerr

Bayesian Optimization (BO) is a surrogate-based global optimization strategy that relies on a Gaussian Process regression (GPR) model to approximate the objective function and an acquisition function to suggest candidate points.

GPR Variable Selection

Extremal GloVe: Theoretically Accurate Distributed Word Embedding by Tail Inference

no code implementations27 Apr 2022 Hao Wang

However, the initial formulation of GloVe is not theoretically sound in two aspects, namely the selection of the weighting function and its power exponent is ad-hoc.

Recommendation Systems Word Embeddings

MovieMat: Context-aware Movie Recommendation with Matrix Factorization by Matrix Fitting

no code implementations27 Apr 2022 Hao Wang

In this paper, we take advantage of the MatMat framework, which factorizes matrices by matrix fitting to build a context-aware movie recommender system that is superior to classic matrix factorization and comparable in the fairness metric.

Collaborative Filtering Fairness +2

KL-Mat : Fair Recommender System via Information Geometry

no code implementations27 Apr 2022 Hao Wang

Recommender system has intrinsic problems such as sparsity and fairness.

Fairness Recommendation Systems

Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks

no code implementations26 Apr 2022 Jiawei Zhang, Jinwei Wang, Hao Wang, Xiangyang Luo

The destruction to DNNs brought by the adversarial attack sparks the potential that adversarial examples serve as a new protection mechanism for privacy security in social networks.

Adversarial Attack

Causal Transportability for Visual Recognition

1 code implementation26 Apr 2022 Chengzhi Mao, Kevin Xia, James Wang, Hao Wang, Junfeng Yang, Elias Bareinboim, Carl Vondrick

Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features.

Image Classification Object Recognition +1

Analyzing the Impact of Undersampling on the Benchmarking and Configuration of Evolutionary Algorithms

no code implementations20 Apr 2022 Diederick Vermetten, Hao Wang, Manuel López-Ibañez, Carola Doerr, Thomas Bäck

Particularly, we show that the number of runs used in many benchmarking studies, e. g., the default value of 15 suggested by the COCO environment, can be insufficient to reliably rank algorithms on well-known numerical optimization benchmarks.

Per-run Algorithm Selection with Warm-starting using Trajectory-based Features

no code implementations20 Apr 2022 Ana Kostovska, Anja Jankovic, Diederick Vermetten, Jacob de Nobel, Hao Wang, Tome Eftimov, Carola Doerr

In contrast to other recent work on online per-run algorithm selection, we warm-start the second optimizer using information accumulated during the first optimization phase.

Time Series Time Series Analysis

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

no code implementations18 Apr 2022 Likang Wu, Hao Wang, Enhong Chen, Zhi Li, Hongke Zhao, Jianhui Ma

To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i. e., preference topics generation, preference shift modeling, and social influence activation.

Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach

no code implementations13 Apr 2022 Xinyu Gao, Wenqiang Yi, Alexandros Agapitos, Hao Wang, Yuanwei Liu

Coverage and capacity are the important metrics for performance evaluation in wireless networks, while the coverage and capacity have several conflicting relationships, e. g. high transmit power contributes to large coverage but high inter-cell interference reduces the capacity performance.

Chaining of Numerical Black-box Algorithms: Warm-Starting and Switching Points

no code implementations13 Apr 2022 Dominik Schröder, Diederick Vermetten, Hao Wang, Carola Doerr, Thomas Bäck

Lastly, with a sensitivity analysis, we find the actual performance gain is hugely affected by the switching point, and in some cases, the switching point yielding the best actual performance differs from the one computed from the theoretical gain.

Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape

no code implementations9 Apr 2022 Xiangyu Zhu, Chang Yu, Di Huang, Zhen Lei, Hao Wang, Stan Z. Li

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.

Context-Sensitive Temporal Feature Learning for Gait Recognition

1 code implementation ICCV 2021 Xiaohu Huang, Duowang Zhu, Xinggang Wang, Hao Wang, Bo Yang, Botao He, Wenyu Liu, Bin Feng

Specifically, CSTL contains an adaptive temporal aggregation module that subsequently performs local relation modeling and global relation modeling to fuse the multi-scale features.

Gait Recognition

ESCM$^2$: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation

no code implementations3 Apr 2022 Hao Wang, Tai-Wei Chang, Tianqiao Liu, Jianmin Huang, Zhichao Chen, Chao Yu, Ruopeng Li, Wei Chu

In this paper, we theoretically demonstrate that ESMM suffers from the following two problems: (1) Inherent Estimation Bias (IEB), where the estimated CVR of ESMM is inherently higher than the ground truth; (2) Potential Independence Priority (PIP) for CTCVR estimation, where there is a risk that the ESMM overlooks the causality from click to conversion.

Recommendation Systems Selection bias

DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

1 code implementation1 Apr 2022 Zihua Zheng, Ni Nie, Zhi Ling, Pengfei Xiong, Jiangyu Liu, Hao Wang, Jiankun Li

Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow.

Optical Flow Estimation

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

1 code implementation29 Mar 2022 WanYu Lin, Hao Lan, Hao Wang, Baochun Li

This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors.

Graph Learning

On Multi-Domain Long-Tailed Recognition, Generalization and Beyond

1 code implementation17 Mar 2022 Yuzhe Yang, Hao Wang, Dina Katabi

We formalize the task of Multi-Domain Long-Tailed Recognition (MDLT), which learns from multi-domain imbalanced data, addresses label imbalance, domain shift, and divergent label distributions across domains, and generalizes to all domain-class pairs.

Domain Generalization

Domain Adaptation with Factorizable Joint Shift

no code implementations6 Mar 2022 Hao He, Yuzhe Yang, Hao Wang

In this paper, we propose a new assumption, Factorizable Joint Shift (FJS), to handle the co-existence of sampling bias in covariates and labels.

Unsupervised Domain Adaptation

Full RGB Just Noticeable Difference (JND) Modelling

no code implementations1 Mar 2022 Jian Jin, Dong Yu, Weisi Lin, Lili Meng, Hao Wang, Huaxiang Zhang

Besides, the JND of the red and blue channels are larger than that of the green one according to the experimental results of the proposed model, which demonstrates that more changes can be tolerated in the red and blue channels, in line with the well-known fact that the human visual system is more sensitive to the green channel in comparison with the red and blue ones.

Image Quality Assessment

Privacy protection based on mask template

no code implementations13 Feb 2022 Hao Wang, Yu Bai, Guangmin Sun, Jie Liu

Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy.

Graph-Relational Domain Adaptation

1 code implementation ICLR 2022 Zihao Xu, Hao He, Guang-He Lee, Yuyang Wang, Hao Wang

In this work, we relax such uniform alignment by using a domain graph to encode domain adjacency, e. g., a graph of states in the US with each state as a domain and each edge indicating adjacency, thereby allowing domains to align flexibly based on the graph structure.

Domain Adaptation

ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning

no code implementations7 Feb 2022 Hao Wang, Zhi Li, Chunpeng Ge, Willy Susilo

To address the issue of privacy-preserving in collaborative learning, secure outsourced computation and federated learning are two typical methods.

Federated Learning

Improved normal-boundary intersection algorithm: a method for energy optimization strategy in smart buildings

no code implementations25 Jan 2022 Jia Cui, Jiang Pan, Shunjiang Wang, Martin Onyeka Okoye, Junyou Yang, Yang Li, Hao Wang

With the widespread use of distributed energy sources, the advantages of smart buildings over traditional buildings are becoming increasingly obvious.

Efficient Data-Plane Memory Scheduling for In-Network Aggregation

no code implementations17 Jan 2022 Hao Wang, Yuxuan Qin, ChonLam Lao, Yanfang Le, Wenfei Wu, Kai Chen

However, switch memory is scarce compared to the volume of gradients transmitted in distributed training.

Mutations make pandemics worse or better: modeling SARS-CoV-2 variants and imperfect vaccination

no code implementations17 Jan 2022 Sarita Bugalia, Jai Prakash Tripathi, Hao Wang

To address the novel dynamics of the disease, we propose a dynamical model of two strains, namely native and mutant, transmission dynamics with mutation and imperfect vaccination.

SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

1 code implementation16 Jan 2022 Hao Wang, Yangguang Li, Zhen Huang, Yong Dou, Lingpeng Kong, Jing Shao

To alleviate feature suppression, we propose contrastive learning for unsupervised sentence embedding with soft negative samples (SNCSE).

Contrastive Learning Data Augmentation +4

From policy to prediction: Forecasting COVID-19 dynamics under imperfect vaccination

no code implementations15 Jan 2022 Xiunan Wang, Hao Wang, Pouria Ramazi, Kyeongah Nah, Mark Lewis

Recently, we created a method in forecasting the daily number of confirmed cases of infectious diseases by combining a mechanistic ordinary differential equation (ODE) model for infectious classes and a generalized boosting machine learning model (GBM) for predicting how public health policies and mobility data affect the transmission rate in the ODE model [WWR+].

Automatic Configuration for Optimal Communication Scheduling in DNN Training

no code implementations27 Dec 2021 Yiqing Ma, Hao Wang, Yiming Zhang, Kai Chen

ByteScheduler partitions and rearranges tensor transmissions to improve the communication efficiency of distributed Deep Neural Network (DNN) training.

Deep Reinforcement Learning for Optimal Power Flow with Renewables Using Spatial-Temporal Graph Information

no code implementations22 Dec 2021 Jinhao Li, Ruichang Zhang, Hao Wang, Zhi Liu, Hongyang Lai, Yanru Zhang

To solve the MOO problem, we develop a novel DRL algorithm leveraging the graphical information of the distribution network.


Continual Learning with Knowledge Transfer for Sentiment Classification

2 code implementations18 Dec 2021 Zixuan Ke, Bing Liu, Hao Wang, Lei Shu

In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain.

Classification Continual Learning +2

Time-of-use Pricing for Energy Storage Investment

no code implementations13 Dec 2021 Dongwei Zhao, Hao Wang, Jianwei Huang, Xiaojun Lin

Such a pricing scheme provides users with incentives to invest in behind-the-meter energy storage and to shift peak load towards low-price intervals.

Gaussian Process Constraint Learning for Scalable Chance-Constrained Motion Planning from Demonstrations

no code implementations8 Dec 2021 Glen Chou, Hao Wang, Dmitry Berenson

We propose a method for learning constraints represented as Gaussian processes (GPs) from locally-optimal demonstrations.

Gaussian Processes Motion Planning

A hypothesis-free bridging of disease dynamics and non-pharmaceutical policies

no code implementations8 Dec 2021 Xiunan Wang, Hao Wang, Pouria Ramazi, Kyeongah Nah, Mark Lewis

Typically, a hypothesis is made on the form of the transmission rate with respect to time.

Merging Subject Matter Expertise and Deep Convolutional Neural Network for State-Based Online Machine-Part Interaction Classification

no code implementations8 Dec 2021 Hao Wang, Yassine Qamsane, James Moyne, Kira Barton

In this work, we address point detection and time series classification for machine-part interactions with a deep Convolutional Neural Network (CNN) based framework.

Change Point Detection Classification +2

ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data

no code implementations6 Dec 2021 Hao Wang

Recommender system is an applicable technique in most E-commerce commercial product technical designs.

Fairness Recommendation Systems

MatMat: Matrix Factorization by Matrix Fitting

no code implementations6 Dec 2021 Hao Wang

Our framework is friendly to multitask learning and side information incorporation.

Fairness Multi-Task Learning +1

Adaptive label thresholding methods for online multi-label classification

no code implementations4 Dec 2021 Tingting Zhai, Hongcheng Tang, Hao Wang

The key feature of our framework is that both scoring and thresholding models are included as important components of the online multi-label classifier and are incorporated into one online optimization problem.

Classification Multi-Label Classification

ProtGNN: Towards Self-Explaining Graph Neural Networks

no code implementations2 Dec 2021 Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, Cheekong Lee

In this work, we propose Prototype Graph Neural Network (ProtGNN), which combines prototype learning with GNNs and provides a new perspective on the explanations of GNNs.

Data privacy protection in microscopic image analysis for material data mining

no code implementations9 Nov 2021 Boyuan Ma, Xiang Yin, Xiaojuan Ban, Haiyou Huang, Neng Zhang, Hao Wang, Weihua Xue

The core contributions are as follows: 1) the federated learning algorithm is introduced into the polycrystalline microstructure image segmentation task to make full use of different user data to carry out machine learning, break the data island and improve the model generalization ability under the condition of ensuring the privacy and security of user data; 2) A data sharing strategy based on style transfer is proposed.

Federated Learning Semantic Segmentation +1

IOHexperimenter: Benchmarking Platform for Iterative Optimization Heuristics

1 code implementation7 Nov 2021 Jacob de Nobel, Furong Ye, Diederick Vermetten, Hao Wang, Carola Doerr, Thomas Bäck

IOHexperimenter can be used as a stand-alone tool or as part of a benchmarking pipeline that uses other components of IOHprofiler such as IOHanalyzer, the module for interactive performance analysis and visualization.

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

E-ffective: A Visual Analytic System for Exploring the Emotion and Effectiveness of Inspirational Speeches

no code implementations28 Oct 2021 Kevin Maher, Zeyuan Huang, Jiancheng Song, Xiaoming Deng, Yu-Kun Lai, Cuixia Ma, Hao Wang, Yong-Jin Liu, Hongan Wang

We further studied the usability of the system by speaking novices and experts on assisting analysis of inspirational speech effectiveness.

Consensus-Based Decentralized Energy Trading for Distributed Energy Resources

no code implementations28 Oct 2021 Zhenyu Wang, XiaoYu Zhang, Hao Wang

In smart grids, distributed energy resources (DERs) have penetrated residential zones to provide a new form of electricity supply, mainly from renewable energy.

Constrained Optimization Involving Nonconvex $\ell_p$ Norms: Optimality Conditions, Algorithm and Convergence

no code implementations27 Oct 2021 Hao Wang, Yining Gao, Jiashan Wang, Hongying Liu

We also derive the sequential optimality conditions for both problems and study the conditions under which these conditions imply the first-order necessary conditions.

Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework

1 code implementation13 Oct 2021 Lu Mi, Tianxing He, Core Francisco Park, Hao Wang, Yue Wang, Nir Shavit

In this work, we show how data labeled with semantically continuous attributes can be utilized to conduct a quantitative evaluation of latent-space interpolation algorithms, for variational autoencoders.

RelationRS: Relationship Representation Network for Object Detection in Aerial Images

no code implementations13 Oct 2021 Zhiming Liu, Xuefei Zhang, Chongyang Liu, Hao Wang, Chao Sun, Bin Li, Weifeng Sun, Pu Huang, Qingjun Li, Yu Liu, Haipeng Kuang, Jihong Xiu

To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution.

Object Detection In Aerial Images

Learning Structural Representations for Recipe Generation and Food Retrieval

no code implementations4 Oct 2021 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

We also validate the usefulness of our learned tree structures in the food cross-modal retrieval task, where the proposed model with tree representations can outperform state-of-the-art benchmark results.

Cross-Modal Retrieval Image Captioning +1

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction

1 code implementation NeurIPS 2021 Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, Chee-Kong Lee

To bridge this gap, we propose Motif-based Graph Self-supervised Learning (MGSSL) by introducing a novel self-supervised motif generation framework for GNNs.

Molecular Property Prediction Self-Supervised Learning

Improving Load Forecast in Energy Markets During COVID-19

no code implementations1 Oct 2021 ZiYun Wang, Hao Wang

The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world.

Load Forecasting

Interpreting Graph Neural Networks via Unrevealed Causal Learning

no code implementations29 Sep 2021 WanYu Lin, Hao Lan, Hao Wang, Baochun Li

This paper proposes a new explanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors.

Graph Learning

Collaborative Three-Stream Transformers for Video Captioning

no code implementations29 Sep 2021 Hao Wang, Longyin Wen, Libo Zhang, Tiejian Luo

In this way, the three branches of transformers can support each other to exploit the most discriminative semantic information in different modalities for accurate predictions of captions, especially for the subject, predicate, and object parts in a sentence.

Video Captioning

Language Models as Recommender Systems: Evaluations and Limitations

no code implementations NeurIPS Workshop ICBINB 2021 Yuhui Zhang, Hao Ding, Zeren Shui, Yifei Ma, James Zou, Anoop Deoras, Hao Wang

Pre-trained language models (PLMs) such as BERT and GPT learn general text representations and encode extensive world knowledge; thus, they can be efficiently and accurately adapted to various downstream tasks.

Session-Based Recommendations

Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values

no code implementations21 Sep 2021 Haewon Jeong, Hao Wang, Flavio P. Calmon

We investigate the fairness concerns of training a machine learning model using data with missing values.

Fairness Imputation

PC$^2$-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsampling

no code implementations20 Sep 2021 Chen Long, Wenxiao Zhang, Ruihui Li, Hao Wang, Zhen Dong, Bisheng Yang

Point cloud upsampling is to densify a sparse point set acquired from 3D sensors, providing a denser representation for the underlying surface.

Critical Learning Periods in Federated Learning

no code implementations12 Sep 2021 Gang Yan, Hao Wang, Jian Li

In this work, we show that the final test accuracy of FL is dramatically affected by the early phase of the training process, i. e., FL exhibits critical learning periods, in which small gradient errors can have irrecoverable impact on the final test accuracy.

Federated Learning

Niche differentiation in the light spectrum promotes coexistence of phytoplankton species: a spatial modelling approach

no code implementations6 Sep 2021 Christopher M. Heggerud, King-Yeung Lam, Hao Wang

The paradox of the plankton highlights the apparent contradiction between Gause's law of competitive exclusion and the observed diversity of phytoplankton.

Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing

no code implementations6 Sep 2021 Xingjian He, Weining Wang, Zhiyong Xu, Hao Wang, Jie Jiang, Jing Liu

Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction.

Scene Parsing

Accelerating Serverless Computing by Harvesting Idle Resources

no code implementations28 Aug 2021 Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, Seung-Jong Park

Serverless computing automates fine-grained resource scaling and simplifies the development and deployment of online services with stateless functions.

Multi-Modulation Network for Audio-Visual Event Localization

no code implementations26 Aug 2021 Hao Wang, Zheng-Jun Zha, Liang Li, Xuejin Chen, Jiebo Luo

We propose a novel MultiModulation Network (M2N) to learn the above correlation and leverage it as semantic guidance to modulate the related auditory, visual, and fused features.

audio-visual event localization

Analyze and Design Network Architectures by Recursion Formulas

no code implementations18 Aug 2021 Yilin Liao, Hao Wang, Zhaoran Liu, Haozhe Li, Xinggao Liu

The effectiveness of shortcut/skip-connection has been widely verified, which inspires massive explorations on neural architecture design.

Cross-Modal Graph with Meta Concepts for Video Captioning

no code implementations14 Aug 2021 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions.

Frame Object Detection +1

UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing

no code implementations12 Aug 2021 Meng Cao, HaoZhi Huang, Hao Wang, Xuan Wang, Li Shen, Sheng Wang, Linchao Bao, Zhifeng Li, Jiebo Luo

Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.

3D Reconstruction Face Reenactment +3

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction

2 code implementations ICCV 2021 Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Ruifeng Deng, Xin Li, Errui Ding, Hao Wang

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks.

Object Detection Style Transfer

Cycle-Consistent Inverse GAN for Text-to-Image Synthesis

no code implementations3 Aug 2021 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

In this paper, we propose a novel unified framework of Cycle-consistent Inverse GAN (CI-GAN) for both text-to-image generation and text-guided image manipulation tasks.

Image Manipulation Text to image generation +1

A Novel Mathematical Model for Infrastructure Planning of Dynamic Wireless Power Transfer Systems for Electric Vehicles

no code implementations23 Jul 2021 Afshin Ghassemi, Laura Soares, Hao Wang, Zhimin Xi

Electric vehicles (EVs) provide an alternative solution that decreases the dependency on traditional fuels such as gasoline and reduces hazardous gas emissions.

Autonomous Driving

STRODE: Stochastic Boundary Ordinary Differential Equation

1 code implementation17 Jul 2021 Hengguan Huang, Hongfu Liu, Hao Wang, Chang Xiao, Ye Wang

In this paper, we present a probabilistic ordinary differential equation (ODE), called STochastic boundaRy ODE (STRODE), that learns both the timings and the dynamics of time series data without requiring any timing annotations during training.

Automatic Speech Recognition Point Processes +1

Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss

1 code implementation16 Jul 2021 Hao Wang, Euijoon Ahn, Jinman Kim

To address these problems, we present a novel self-supervised spatiotemporal learning framework for remote physiological signal representation learning, where there is a lack of labelled training data.

Contrastive Learning Data Augmentation +3

Adaptive 3D descattering with a dynamic synthesis network

1 code implementation1 Jul 2021 Waleed Tahir, Hao Wang, Lei Tian

In addition, we show that by training the DSN entirely on simulated data, the network can generalize to experiments and achieve robust 3D descattering.


Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval

1 code implementation22 Jun 2021 Zhipeng Wang, Hao Wang, Jiexi Yan, Aming Wu, Cheng Deng

Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches.

Cross-Modal Retrieval Sketch-Based Image Retrieval

LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-Resolution

no code implementations CVPR 2021 Xin Deng, Hao Wang, Mai Xu, Yichen Guo, Yuhang Song, Li Yang

In addition, we propose a deep reinforcement learning scheme with a latitude adaptive reward, in order to automatically select optimal upscaling factors for different latitude bands.

Image Super-Resolution

Structured Multi-Level Interaction Network for Video Moment Localization via Language Query

no code implementations CVPR 2021 Hao Wang, Zheng-Jun Zha, Liang Li, Dong Liu, Jiebo Luo

In particular, for cross-modal interaction, we interact the sentence-level query with the whole moment while interact the word-level query with content and boundary, as in a coarse-to-fine manner.


Enhancing Question Generation with Commonsense Knowledge

no code implementations CCL 2021 Xin Jia, Hao Wang, Dawei Yin, Yunfang Wu

Question generation (QG) is to generate natural and grammatical questions that can be answered by a specific answer for a given context.

Multi-Task Learning Question Generation +1

Correcting Exposure Bias for Link Recommendation

1 code implementation13 Jun 2021 Shantanu Gupta, Hao Wang, Zachary C. Lipton, Yuyang Wang

Link prediction methods are frequently applied in recommender systems, e. g., to suggest citations for academic papers or friends in social networks.

Link Prediction Recommendation Systems

Automated Configuration of Genetic Algorithms by Tuning for Anytime Performance

1 code implementation11 Jun 2021 Furong Ye, Carola Doerr, Hao Wang, Thomas Bäck

Finding the best configuration of algorithms' hyperparameters for a given optimization problem is an important task in evolutionary computation.

Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems

no code implementations9 Jun 2021 Yinan Zhang, Boyang Li, Yong liu, Hao Wang, Chunyan Miao

In this work, we propose a new initialization scheme for user and item embeddings called Laplacian Eigenmaps with Popularity-based Regularization for Isolated Data (LEPORID).

Recommendation Systems

DMBGN: Deep Multi-Behavior Graph Networks for Voucher Redemption Rate Prediction

1 code implementation7 Jun 2021 Fengtong Xiao, Lin Li, Weinan Xu, Jingyu Zhao, Xiaofeng Yang, Jun Lang, Hao Wang

In this paper, we propose a Deep Multi-behavior Graph Networks (DMBGN) to shed light on this field for the voucher redemption rate prediction.

GraphMI: Extracting Private Graph Data from Graph Neural Networks

1 code implementation5 Jun 2021 Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang, Chengqiang Lu, Chuanren Liu, Enhong Chen

Then we design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference.

Characterizing Residential Load Patterns by Household Demographic and Socioeconomic Factors

no code implementations4 Jun 2021 Zhuo Wei, Hao Wang

We develop a deep neural network (DNN) to analyze the relationship between users' load patterns and their demographic and socioeconomic features.

Smart Online Charging Algorithm for Electric Vehicles via Customized Actor-Critic Learning

no code implementations1 Jun 2021 Yongsheng Cao, Hao Wang, Demin Li, Guanglin Zhang

First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information.

Zipf Matrix Factorization : Matrix Factorization with Matthew Effect Reduction

1 code implementation1 Jun 2021 Hao Wang

We demonstrate that our approach can boost the fairness of the algorithm and enhances performance evaluated by traditional metrics.

Fairness Learning-To-Rank +1

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification

1 code implementation25 May 2021 Guoqing Zhang, Yu Ge, Zhicheng Dong, Hao Wang, yuhui Zheng, ShengYong Chen

Compared with the state-of-the-art methods, our proposed PS-HRNet improves 3. 4\%, 6. 2\%, 2. 5\%, 1. 1\% and 4. 2\% at Rank-1 on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets, respectively.

Person Re-Identification Representation Learning

Zero-Shot Recommender Systems

no code implementations18 May 2021 Hao Ding, Yifei Ma, Anoop Deoras, Yuyang Wang, Hao Wang

This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS.

Recommendation Systems Zero-Shot Learning

KECRS: Towards Knowledge-Enriched Conversational Recommendation System

no code implementations18 May 2021 Tong Zhang, Yong liu, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions.

Entity Embeddings Knowledge Graphs +3

Quantifying the Impact of Boundary Constraint Handling Methods on Differential Evolution

no code implementations14 May 2021 Rick Boks, Anna V. Kononova, Hao Wang

Constraint handling is one of the most influential aspects of applying metaheuristics to real-world applications, which can hamper the search progress if treated improperly.

Learning to Ask Appropriate Questions in Conversational Recommendation

no code implementations11 May 2021 Xuhui Ren, Hongzhi Yin, Tong Chen, Hao Wang, Zi Huang, Kai Zheng

Hence, the ability to generate suitable clarifying questions is the key to timely tracing users' dynamic preferences and achieving successful recommendations.

Question Generation Recommendation Systems

Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech

no code implementations10 May 2021 Pengwei Wang, Xin Ye, Xiaohuan Zhou, Jinghui Xie, Hao Wang

In contrast to conventional pipeline Spoken Language Understanding (SLU) which consists of automatic speech recognition (ASR) and natural language understanding (NLU), end-to-end SLU infers the semantic meaning directly from speech and overcomes the error propagation caused by ASR.

Automatic Speech Recognition Natural Language Understanding +3

Is there Anisotropy in Structural Bias?

no code implementations10 May 2021 Diederick Vermetten, Anna V. Kononova, Fabio Caraffini, Hao Wang, Thomas Bäck

We find that anisotropy is very rare, and even in cases where it is present, there are clear tests for SB which do not rely on any assumptions of isotropy, so we can safely expand the suite of SB tests to encompass these kinds of deficiencies not found by the original tests.

Covariance Matrix Adaptation Evolution Strategy Assisted by Principal Component Analysis

no code implementations8 May 2021 Yangjie Mei, Hao Wang

Over the past decades, more and more methods gain a giant development due to the development of technology.

Dimensionality Reduction

Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant

no code implementations1 May 2021 Qing Yang, Hao Wang, Taotao Wang, Shengli Zhang, Xiaoxiao Wu, Hui Wang

In this paper, we develop a blockchain-based VPP energy management platform to facilitate a rich set of transactive energy activities among residential users with renewables, energy storage, and flexible loads in a VPP.

Distributed Energy Trading Management for Renewable Prosumers with HVAC and Energy Storage

no code implementations1 May 2021 Qing Yang, Hao Wang

This work develops a novel distributed method for the residential transactive energy system that enables multiple users to interactively optimize their energy management of HVAC systems and behind-the-meter batteries.

Distributed Optimization

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

Explorative Data Analysis of Time Series based AlgorithmFeatures of CMA-ES Variants

no code implementations16 Apr 2021 Jacob de Nobel, Hao Wang, Thomas Bäck

From our analysis, we saw that the features can classify the CMA-ES variants, or the function groups decently, and show a potential for predicting the performance of those variants.

feature selection Time Series

Machine Learning Approach to Uncovering Residential Energy Consumption Patterns Based on Socioeconomic and Smart Meter Data

no code implementations12 Apr 2021 Wenjun Tang, Hao Wang, Xian-Long Lee, Hong-Tzer Yang

We model consumption patterns by representative loads and reveal the relationship between load patterns and socioeconomic characteristics.

feature selection

An Iteratively Reweighted Method for Sparse Optimization on Nonconvex $\ell_{p}$ Ball

no code implementations7 Apr 2021 Hao Wang, Xiangyu Yang, Wei Jiang

Specifically, if the current iterate is in the interior of the feasible set, then the weighted $\ell_{1}$ ball is formed by linearizing the $\ell_{p}$ norm at the current iterate.

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

no code implementations4 Apr 2021 Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang

In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.

Graph Representation Learning

Scene Text Retrieval via Joint Text Detection and Similarity Learning

1 code implementation CVPR 2021 Hao Wang, Xiang Bai, Mingkun Yang, Shenggao Zhu, Jing Wang, Wenyu Liu

Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-end scene text spotter.

Scene Text Detection Text Spotting

Adversarial Attacks are Reversible with Natural Supervision

1 code implementation ICCV 2021 Chengzhi Mao, Mia Chiquier, Hao Wang, Junfeng Yang, Carl Vondrick

We find that images contain intrinsic structure that enables the reversal of many adversarial attacks.

Any Part of Bayesian Network Structure Learning

no code implementations23 Mar 2021 Zhaolong Ling, Kui Yu, Hao Wang, Lin Liu, Jiuyong Li

We study an interesting and challenging problem, learning any part of a Bayesian network (BN) structure.

feature selection

Potential Advantages of Peak Picking Multi-Voltage Threshold Digitizer in Energy Determination in Radiation Measurement

no code implementations8 Mar 2021 Kezhang Zhu, Junhua Mei, Yuming Su, Pingping Dai, Nicola D'Ascenzo, Hao Wang, Peng Xiao, Lin Wan, Qingguo Xie

After processing 30, 000 randomly-chosen pulses sampled by the oscilloscope with a 22Na point source, our method achieves an energy resolution of 17. 50% within a 450-650 KeV energy window, which is 2. 44% better than the result of traditional MVT with same thresholds; and we get a count number at 15225 in the same energy window while the result of MVT is at 14678.

Towards Efficient Local Causal Structure Learning

no code implementations28 Feb 2021 Shuai Yang, Hao Wang, Kui Yu, Fuyuan Cao, Xindong Wu

Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data.

Tuning as a Means of Assessing the Benefits of New Ideas in Interplay with Existing Algorithmic Modules

no code implementations25 Feb 2021 Jacob de Nobel, Diederick Vermetten, Hao Wang, Carola Doerr, Thomas Bäck

However, when introducing a new component into an existing algorithm, assessing its potential benefits is a challenging task.

Residual-Aided End-to-End Learning of Communication System without Known Channel

no code implementations22 Feb 2021 Hao Jiang, Shuangkaisheng Bi, Linglong Dai, Hao Wang, Jiankun Zhang

However, the gradient vanishing and overfitting problems of GAN will result in the serious performance degradation of E2E learning of communication system.

Back to Prior Knowledge: Joint Event Causality Extraction via Convolutional Semantic Infusion

no code implementations19 Feb 2021 Zijian Wang, Hao Wang, Xiangfeng Luo, Jianqi Gao

Joint event and causality extraction is a challenging yet essential task in information retrieval and data mining.

Information Retrieval

Delving into Deep Imbalanced Regression

1 code implementation18 Feb 2021 Yuzhe Yang, Kaiwen Zha, Ying-Cong Chen, Hao Wang, Dina Katabi

We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range.

Temporal Memory Attention for Video Semantic Segmentation

1 code implementation17 Feb 2021 Hao Wang, Weining Wang, Jing Liu

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence.

Frame Semantic Segmentation +1

Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram

no code implementations3 Feb 2021 Shengkui Zhao, Hao Wang, Trung Hieu Nguyen, Bin Ma

Cross-lingual voice conversion (VC) is an important and challenging problem due to significant mismatches of the phonetic set and the speech prosody of different languages.

Voice Conversion

Network Clustering for Multi-task Learning

no code implementations22 Jan 2021 Dehong Gao, Wenjing Yang, Huiling Zhou, Yi Wei, Yi Hu, Hao Wang

The majority of current MTL studies adopt the hard parameter sharing structure, where hard layers tend to learn general representations over all tasks and specific layers are prone to learn specific representations for each task.

Document Classification Multi-Task Learning

Privacy-Preserving Transactive Energy Management for IoT-aided Smart Homes via Blockchain

no code implementations11 Jan 2021 Qing Yang, Hao Wang

Further, we design an efficient blockchain system tailored for IoT devices and develop the smart contract to support the holistic transactive energy management system.

Learning Guided Electron Microscopy with Active Acquisition

1 code implementation7 Jan 2021 Lu Mi, Hao Wang, Yaron Meirovitch, Richard Schalek, Srinivas C. Turaga, Jeff W. Lichtman, Aravinthan D. T. Samuel, Nir Shavit

Single-beam scanning electron microscopes (SEM) are widely used to acquire massive data sets for biomedical study, material analysis, and fabrication inspection.

Towards An Efficient Approach for the Nonconvex $\ell_p$ Ball Projection: Algorithm and Analysis

2 code implementations5 Jan 2021 Xiangyu Yang, Jiashan Wang, Hao Wang

This paper primarily focuses on computing the Euclidean projection of a vector onto the $\ell_{p}$ ball in which $p\in(0, 1)$.

Recurrent Exploration Networks for Recommender Systems

no code implementations1 Jan 2021 Hao Wang, Yifei Ma, Hao Ding, Bernie Wang

Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems.

Recommendation Systems Representation Learning

Self-Supervised Vessel Segmentation via Adversarial Learning

1 code implementation ICCV 2021 Yuxin Ma, Yang Hua, Hanming Deng, Tao Song, Hao Wang, Zhengui Xue, Heng Cao, Ruhui Ma, Haibing Guan

Vessel segmentation is critically essential for diagnosinga series of diseases, e. g., coronary artery disease and retinal disease.

Domain Adaptation

HCGrid: A Convolution-based Gridding Framework for RadioAstronomy in Hybrid Computing Environments

1 code implementation24 Dec 2020 Hao Wang, Ce Yu, Bo Zhang, Jian Xiao, Qi Luo

Gridding operation, which is to map non-uniform data samples onto a uniformly distributedgrid, is one of the key steps in radio astronomical data reduction process.

Instrumentation and Methods for Astrophysics

Generative Interventions for Causal Learning

1 code implementation CVPR 2021 Chengzhi Mao, Augustine Cha, Amogh Gupta, Hao Wang, Junfeng Yang, Carl Vondrick

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts.

Out-of-Distribution Generalization

Catalytically Potent and Selective Clusterzymes for Modulation of Neuroinflammation Through Single-Atom Substitutions

no code implementations17 Dec 2020 Haile Liu, Yonghui Li, Si Sun, Qi Xin, Shuhu Liu, Xiaoyu Mu, Xun Yuan, Ke Chen, Hao Wang, Kalman Varga, Wenbo Mi, Jiang Yang, Xiao-Dong Zhang

Emerging artificial enzymes with reprogrammed and augmented catalytic activity and substrate selectivity have long been pursued with sustained efforts.

Biological Physics Medical Physics

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

no code implementations15 Dec 2020 Peixiang Zhong, Di Wang, Pengfei Li, Chen Zhang, Hao Wang, Chunyan Miao

Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.

Response Generation

Keyword-Guided Neural Conversational Model

no code implementations15 Dec 2020 Peixiang Zhong, Yong liu, Hao Wang, Chunyan Miao

We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast.

Knowledge Graphs Word Embeddings

Federated Learning for Personalized Humor Recognition

no code implementations3 Dec 2020 Xu Guo, Han Yu, Boyang Li, Hao Wang, Pengwei Xing, Siwei Feng, Zaiqing Nie, Chunyan Miao

In this paper, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL).

Federated Learning Language Modelling

Learning Spatial Attention for Face Super-Resolution

1 code implementation2 Dec 2020 Chaofeng Chen, Dihong Gong, Hao Wang, Zhifeng Li, Kwan-Yee K. Wong

Visualization of the attention maps shows that our spatial attention network can capture the key face structures well even for very low resolution faces (e. g., $16\times16$).

Face Parsing Image Super-Resolution +2

On Statistical Analysis of MOEAs with Multiple Performance Indicators

1 code implementation1 Dec 2020 Hao Wang, Carlos Igncio Hernández Castellanos, Tome Eftimov

Assessing the empirical performance of Multi-Objective Evolutionary Algorithms (MOEAs) is vital when we extensively test a set of MOEAs and aim to determine a proper ranking thereof.

Argumentation Mining on Essays at Multi Scales

no code implementations COLING 2020 Hao Wang, Zhen Huang, Yong Dou, Yu Hong

Recent research mainly models the task as a sequence tagging problem and deal with all the argumentation components at word level.

Face Forgery Detection by 3D Decomposition

no code implementations CVPR 2021 Xiangyu Zhu, Hao Wang, Hongyan Fei, Zhen Lei, Stan Z. Li

Detecting digital face manipulation has attracted extensive attention due to fake media's potential harms to the public.

Learning causal representations for robust domain adaptation

no code implementations12 Nov 2020 Shuai Yang, Kui Yu, Fuyuan Cao, Lin Liu, Hao Wang, Jiuyong Li

In this paper, we study the cases where at the training phase the target domain data is unavailable and only well-labeled source domain data is available, called robust domain adaptation.

Domain Adaptation

MatRec: Matrix Factorization for Highly Skewed Dataset

no code implementations9 Nov 2020 Hao Wang, Bing Ruan

Recommender systems is one of the most successful AI technologies applied in the internet cooperations.

Learning-To-Rank Recommendation Systems

Neural Network Design: Learning from Neural Architecture Search

1 code implementation1 Nov 2020 Bas van Stein, Hao Wang, Thomas Bäck

Neural Architecture Search (NAS) aims to optimize deep neural networks' architecture for better accuracy or smaller computational cost and has recently gained more research interests.

Image Classification Neural Architecture Search

Cooperative Energy Management of HVAC via Transactive Energy

no code implementations26 Oct 2020 Qing Yang, Hao Wang

However, how to scale up HVAC energy management for a group of users while persevering users' privacy remains a big challenge.

Total Energy

Activity Detection And Modeling Using Smart Meter Data: Concept And Case Studies

no code implementations26 Oct 2020 Hao Wang, Gonzague Henri, Chin-Woo Tan, Ram Rajagopal

Electricity consumed by residential consumers counts for a significant part of global electricity consumption and utility companies can collect high-resolution load data thanks to the widely deployed advanced metering infrastructure.

Action Detection Activity Detection

COSEA: Convolutional Code Search with Layer-wise Attention

no code implementations19 Oct 2020 Hao Wang, Jia Zhang, Yingce Xia, Jiang Bian, Chao Zhang, Tie-Yan Liu

However, most existing studies overlook the code's intrinsic structural logic, which indeed contains a wealth of semantic information, and fails to capture intrinsic features of codes.

Code Search

Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion

1 code implementation16 Oct 2020 Shengkui Zhao, Trung Hieu Nguyen, Hao Wang, Bin Ma

With these data, three neural TTS models -- Tacotron2, Transformer and FastSpeech are applied for building bilingual and code-switched TTS.

Speech Synthesis Voice Conversion

Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples

no code implementations2 Oct 2020 Chao Tao, Ji Qi, Weipeng Lu, Hao Wang, Haifeng Li

With the development of deep learning, supervised learning methods perform well in remote sensing images (RSIs) scene classification.

Classification General Classification +2

Contract-based Time-of-use Pricing for Energy Storage Investment

no code implementations26 Sep 2020 Dongwei Zhao, Hao Wang, Jianwei Huang, Xiaojun Lin

We also show that the proposed contracts can reduce the system social cost by over 30%, compared with no storage investment benchmark.

Systems and Control Systems and Control

Detection Defense Against Adversarial Attacks with Saliency Map

no code implementations6 Sep 2020 Dengpan Ye, Chuanxi Chen, Changrui Liu, Hao Wang, Shunzhi Jiang

Our experimental results of some representative adversarial attacks on common datasets including ImageNet and popular models show that our method can detect all the attacks with high detection success rate effectively.

Structure-Aware Generation Network for Recipe Generation from Images

1 code implementation ECCV 2020 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

We investigate an open research task of generating cooking instructions based on only food images and ingredients, which is similar to the image captioning task.

Image Captioning Recipe Generation

When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control

no code implementations20 Aug 2020 Chaochao Chen, Jun Zhou, Li Wang, Xibin Wu, Wenjing Fang, Jin Tan, Lei Wang, Alex X. Liu, Hao Wang, Cheng Hong

In this paper, we first present CAESAR, which combines HE and SS to build secure large-scale sparse logistic regression model and achieves both efficiency and security.

Domain-specific Communication Optimization for Distributed DNN Training

no code implementations16 Aug 2020 Hao Wang, Jingrong Chen, Xinchen Wan, Han Tian, Jiacheng Xia, Gaoxiong Zeng, Weiyan Wang, Kai Chen, Wei Bai, Junchen Jiang

Communication overhead poses an important obstacle to distributed DNN training and draws increasing attention in recent years.

Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective

no code implementations31 Jul 2020 Yinghuan Shi, Wanqi Yang, Kim-Han Thung, Hao Wang, Yang Gao, Yang Pan, Li Zhang, Dinggang Shen

Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.

Decomposing Generation Networks with Structure Prediction for Recipe Generation

no code implementations27 Jul 2020 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality.

Image Captioning Recipe Generation

IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics

4 code implementations8 Jul 2020 Hao Wang, Diederick Vermetten, Furong Ye, Carola Doerr, Thomas Bäck

An R programming interface is provided for users preferring to have a finer control over the implemented functionalities.

ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction

1 code implementation7 Jul 2020 Zhongkai Hao, Chengqiang Lu, Zheyuan Hu, Hao Wang, Zhenya Huang, Qi Liu, Enhong Chen, Cheekong Lee

Here we propose a novel framework called Active Semi-supervised Graph Neural Network (ASGN) by incorporating both labeled and unlabeled molecules.

Active Learning Molecular Property Prediction

Deep Graph Random Process for Relational-Thinking-Based Speech Recognition

no code implementations ICML 2020 Hengguan Huang, Fuzhao Xue, Hao Wang, Ye Wang

Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation of these percepts.

Automatic Speech Recognition

Task-agnostic Temporally Consistent Facial Video Editing

no code implementations3 Jul 2020 Meng Cao, Hao-Zhi Huang, Hao Wang, Xuan Wang, Li Shen, Sheng Wang, Linchao Bao, Zhifeng Li, Jiebo Luo

Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.

3D Reconstruction Frame

Continuously Indexed Domain Adaptation

1 code implementation ICML 2020 Hao Wang, Hao He, Dina Katabi

Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.

Continuously Indexed Domain Adaptation

High Dimensional Bayesian Optimization Assisted by Principal Component Analysis

1 code implementation2 Jul 2020 Elena Raponi, Hao Wang, Mariusz Bujny, Simonetta Boria, Carola Doerr

Bayesian Optimization (BO) is a surrogate-assisted global optimization technique that has been successfully applied in various fields, e. g., automated machine learning and design optimization.


Continuously Index Domain Adaptation

1 code implementation ICML 2020 Hao Wang, Hao He, Dina Katabi

Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.

Continuously Indexed Domain Adaptation

A Modular Hybridization of Particle Swarm Optimization and Differential Evolution

1 code implementation21 Jun 2020 Rick Boks, Hao Wang, Thomas Bäck

In swarm intelligence, Particle Swarm Optimization (PSO) and Differential Evolution (DE) have been successfully applied in many optimization tasks, and a large number of variants, where novel algorithm operators or components are implemented, has been introduced to boost the empirical performance.

Towards Dynamic Algorithm Selection for Numerical Black-Box Optimization: Investigating BBOB as a Use Case

1 code implementation11 Jun 2020 Diederick Vermetten, Hao Wang, Carola Doerr, Thomas Bäck

One of the most challenging problems in evolutionary computation is to select from its family of diverse solvers one that performs well on a given problem.

Benchmarking a $(μ+λ)$ Genetic Algorithm with Configurable Crossover Probability

no code implementations10 Jun 2020 Furong Ye, Hao Wang, Carola Doerr, Thomas Bäck

Moreover, we observe that the ``fast'' mutation scheme with its are power-law distributed mutation strengths outperforms standard bit mutation on complex optimization tasks when it is combined with crossover, but performs worse in the absence of crossover.

FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval

3 code implementations20 May 2020 Dehong Gao, Linbo Jin, Ben Chen, Minghui Qiu, Peng Li, Yi Wei, Yi Hu, Hao Wang

In this paper, we address the text and image matching in cross-modal retrieval of the fashion industry.

Cross-Modal Retrieval

Towards Persona-Based Empathetic Conversational Models

1 code implementation EMNLP 2020 Peixiang Zhong, Chen Zhang, Hao Wang, Yong liu, Chunyan Miao

To this end, we propose a new task towards persona-based empathetic conversations and present the first empirical study on the impact of persona on empathetic responding.

Secret Sharing based Secure Regressions with Applications

no code implementations10 Apr 2020 Chaochao Chen, Liang Li, Wenjing Fang, Jun Zhou, Li Wang, Lei Wang, Shuang Yang, Alex Liu, Hao Wang

Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns.

Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval

no code implementations22 Mar 2020 Xinxun Xu, Muli Yang, Yanhua Yang, Hao Wang

Specifically, with the supervision of original semantic knowledge, PDFD decomposes visual features into domain features and semantic ones, and then the semantic features are projected into common space as retrieval features for ZS-SBIR.

Cross-Modal Retrieval Sketch-Based Image Retrieval

Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism

no code implementations9 Mar 2020 Hao Wang, Doyen Sahoo, Chenghao Liu, Ke Shu, Palakorn Achananuparp, Ee-Peng Lim, Steven C. H. Hoi

Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc.

Cross-Modal Retrieval

Towards information-rich, logical text generation with knowledge-enhanced neural models

no code implementations2 Mar 2020 Hao Wang, Bin Guo, Wei Wu, Zhiwen Yu

Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life.

Text Generation