Search Results for author: Zhi Wang

Found 45 papers, 15 papers with code

SeqNet: An Efficient Neural Network for Automatic Malware Detection

no code implementations8 May 2022 Jiawei Xu, Wenxuan Fu, Haoyu Bu, Zhi Wang, Lingyun Ying

We demonstrate the effectiveness of our methods and the low training cost requirement of SeqNet in our experiments.

Feature Engineering Malware Analysis +1

Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach

1 code implementation29 Apr 2022 Shuzhao Xie, Yuan Xue, Yifei Zhu, Zhi Wang

With the advancement of deep learning techniques, major cloud providers and niche machine learning service providers start to offer their cloud-based machine learning tools, also known as machine learning as a service (MLaaS), to the public.


Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach

no code implementations21 Apr 2022 Chen Tang, Haoyu Zhai, Kai Ouyang, Zhi Wang, Yifei Zhu, Wenwu Zhu

We propose to feed different data samples with varying quantization schemes to achieve a data-dependent dynamic inference, at a fine-grained layer level.


Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning

no code implementations16 Apr 2022 Jinmei Liu, Zhi Wang, Chunlin Chen, Daoyi Dong

Second, BPR algorithms usually require numerous samples to estimate the probability distribution of the tabular-based observation model, which may be expensive and even infeasible to learn and maintain, especially when using the state transition sample as the signal.

Continual Learning reinforcement-learning

Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance

no code implementations16 Mar 2022 Chen Tang, Kai Ouyang, Zhi Wang, Yifei Zhu, YaoWei Wang, Wen Ji, Wenwu Zhu

The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer.


A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach

no code implementations10 Mar 2022 Xiaohan Lan, Yitian Yuan, Xin Wang, Long Chen, Zhi Wang, Lin Ma, Wenwu Zhu

New benchmarking results indicate that our proposed evaluation protocols can better monitor the research progress.

Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation

no code implementations6 Mar 2022 Donghan Xie, Zhi Wang, Chunlin Chen, Daoyi Dong

In this paper, we propose a new method based on local communication learning to tackle the multi-agent RL (MARL) challenge within a large number of agents coexisting.

SMAC Starcraft +1

Fully Self-Supervised Learning for Semantic Segmentation

no code implementations24 Feb 2022 YuAn Wang, Wei Zhuo, Yucong Li, Zhi Wang, Qi Ju, Wenwu Zhu

To solve this problem, we proposed a bootstrapped training scheme for semantic segmentation, which fully leveraged the global semantic knowledge for self-supervision with our proposed PGG strategy and CAE module.

Self-Supervised Learning Unsupervised Semantic Segmentation

bert2BERT: Towards Reusable Pretrained Language Models

no code implementations ACL 2022 Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, Qun Liu

However, large language model pre-training costs intensive computational resources and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful.

Language Modelling Pretrained Language Models

OVD-Explorer: A General Information-theoretic Exploration Approach for Reinforcement Learning

no code implementations29 Sep 2021 Jinyi Liu, Zhi Wang, Yan Zheng, Jianye Hao, Junjie Ye, Chenjia Bai, Pengyi Li

Many exploration strategies are built upon the optimism in the face of the uncertainty (OFU) principle for reinforcement learning.


A Survey on Temporal Sentence Grounding in Videos

no code implementations16 Sep 2021 Xiaohan Lan, Yitian Yuan, Xin Wang, Zhi Wang, Wenwu Zhu

In this survey, we give a comprehensive overview for TSGV, which i) summarizes the taxonomy of existing methods, ii) provides a detailed description of the evaluation protocols(i. e., datasets and metrics) to be used in TSGV, and iii) in-depth discusses potential problems of current benchmarking designs and research directions for further investigations.

Temporal Action Localization

EvilModel 2.0: Bringing Neural Network Models into Malware Attacks

1 code implementation9 Sep 2021 Zhi Wang, Chaoge Liu, Xiang Cui, Jie Yin, Xutong Wang

However, the existing works have not shown that this emerging threat is practical in real-world attacks because of the low malware embedding rate, the high model performance degradation and the extra efforts.

EvilModel: Hiding Malware Inside of Neural Network Models

1 code implementation19 Jul 2021 Zhi Wang, Chaoge Liu, Xiang Cui

In this paper, we present a new method to covertly and evasively deliver malware through a neural network model.

Online Continual Adaptation with Active Self-Training

no code implementations11 Jun 2021 Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang, Heng Chang, Zhi Wang, Wenwu Zhu

Our theoretical results show that OSAMD can fast adapt to changing environments with active queries.

online learning

Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation

no code implementations24 Apr 2021 Cheng Chen, Yichun Yin, Lifeng Shang, Zhi Wang, Xin Jiang, Xiao Chen, Qun Liu

Task-agnostic knowledge distillation, a teacher-student framework, has been proved effective for BERT compression.

Knowledge Distillation

Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction

no code implementations15 Apr 2021 Yuanyang Zhu, Zhi Wang, Chunlin Chen, Daoyi Dong

In this paper, we focus on efficient navigation with the RL technique and combine the advantages of these two kinds of methods into a rule-based RL (RuRL) algorithm for reducing the sample complexity and cost of time.

reinforcement-learning Robot Navigation +1

Deepfake Forensics via An Adversarial Game

no code implementations25 Mar 2021 Zhi Wang, Yiwen Guo, WangMeng Zuo

In this paper, we advocate adversarial training for improving the generalization ability to both unseen facial forgeries and unseen image/video qualities.

Classification DeepFake Detection +2

Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models

1 code implementation7 Mar 2021 Linghan Meng, Yanhui Li, Lin Chen, Zhi Wang, Di wu, Yuming Zhou, Baowen Xu

To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i. e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance.

Spin-orbit driven ferromagnetism at half moiré filling in magic-angle twisted bilayer graphene

no code implementations12 Feb 2021 Jiang-Xiazi Lin, Ya-Hui Zhang, Erin Morissette, Zhi Wang, Song Liu, Daniel Rhodes, K. Watanabe, T. Taniguchi, James Hone, J. I. A. Li

Strong electron correlation and spin-orbit coupling (SOC) provide two non-trivial threads to condensed matter physics.

Mesoscale and Nanoscale Physics Materials Science Strongly Correlated Electrons

A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric

no code implementations22 Jan 2021 Yitian Yuan, Xiaohan Lan, Xin Wang, Long Chen, Zhi Wang, Wenwu Zhu

All the results demonstrate that the re-organized dataset splits and new metric can better monitor the progress in TSGV.

Polymorphous density-functional description of paramagnetic phases of quantum magnets

no code implementations7 Jan 2021 Yufei Zhao, Qiushi Yao, PengFei Liu, Jingzhi Han, Zhi Wang, Qihang Liu

The kernel of the study of magnetic quantum materials focuses on the magnetic phase transitions, among which the most common phenomenon is the transition between low-temperature magnetic-ordered phase to high-temperature paramagnetic phase.

Materials Science

MQES: Max-Q Entropy Search for Efficient Exploration in Continuous Reinforcement Learning

no code implementations1 Jan 2021 Jinyi Liu, Zhi Wang, Jianye Hao, Yan Zheng

Recently, the principle of optimism in the face of (aleatoric and epistemic) uncertainty has been utilized to design efficient exploration strategies for Reinforcement Learning (RL).

Efficient Exploration reinforcement-learning

Tinker-HP : Accelerating Molecular Dynamics Simulations of Large Complex Systems with Advanced Point Dipole Polarizable Force Fields using GPUs and Multi-GPUs systems

2 code implementations2 Nov 2020 Olivier Adjoua, Louis Lagardère, Luc-Henri Jolly, Arnaud Durocher, Thibaut Very, Isabelle Dupays, Zhi Wang, Théo Jaffrelot Inizan, Frédéric Célerse, Pengyu Ren, Jay W. Ponder, Jean-Philip Piquemal

Perspectives toward the strong-scaling performance of our multi-node massive parallelization strategy, unsupervised adaptive sampling and large scale applicability of the Tinker-HP code in biophysics are discussed.

Computational Physics Distributed, Parallel, and Cluster Computing Mathematical Software Chemical Physics

Multitask Bandit Learning Through Heterogeneous Feedback Aggregation

1 code implementation29 Oct 2020 Zhi Wang, Chicheng Zhang, Manish Kumar Singh, Laurel D. Riek, Kamalika Chaudhuri

In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol.

CryptMPI: A Fast Encrypted MPI Library

1 code implementation13 Oct 2020 Abu Naser, Cong Wu, Mehran Sadeghi Lahijani, Mohsen Gavahi, Viet Tung Hoang, Zhi Wang, Xin Yuan

The cloud infrastructure must provide security for High-Performance Computing (HPC) applications of sensitive data to execute in such an environment.

Distributed, Parallel, and Cluster Computing Cryptography and Security

Performance Evaluation and Modeling of Cryptographic Libraries for MPI Communications

1 code implementation13 Oct 2020 Abu Naser, Mehran Sadeghi Lahijani, Cong Wu, Mohsen Gavahi, Viet Tung Hoang, Zhi Wang, Xin Yuan

In order for High-Performance Computing (HPC) applications with data security requirements to execute in the public cloud, the cloud infrastructure must ensure the privacy and integrity of data.

Distributed, Parallel, and Cluster Computing Cryptography and Security

Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments

1 code implementation9 Oct 2020 Zhi Wang, Chunlin Chen, Daoyi Dong

Instance novelty measures an instance's difference from the previous optimum in the original environment, while instance quality corresponds to how well an instance performs in the new environment.

Incremental Learning Q-Learning +2

DeepC2: AI-powered Covert Botnet Command and Control on OSNs

no code implementations16 Sep 2020 Zhi Wang, Chaoge Liu, Xiang Cui, Jiaxi Liu, Di wu, Jie Yin

Experiments on Twitter show that command-embedded contents can be generated efficiently, and bots can find botmasters and obtain commands accurately.

Data Augmentation

Neurodynamic TDOA localization with NLOS mitigation via maximum correntropy criterion

no code implementations14 Sep 2020 Wenxin Xiong, Christian Schindelhauer, Hing Cheung So, Junli Liang, Zhi Wang

In this paper, we exploit the maximum correntropy criterion (MCC) to robustify the traditional time-difference-of-arrival (TDOA) location estimator in the presence of non-line-of-sight (NLOS) propagation conditions.

Maximum correntropy criterion for robust TOA-based localization in NLOS environments

no code implementations13 Sep 2020 Wenxin Xiong, Christian Schindelhauer, Hing Cheung So, Zhi Wang

We investigate the problem of time-of-arrival (TOA) based localization under possible non-line-of-sight (NLOS) propagation conditions.

Subtask Analysis of Process Data Through a Predictive Model

no code implementations29 Aug 2020 Zhi Wang, Xueying Tang, Jingchen Liu, Zhiliang Ying

Response process data collected from human-computer interactive items contain rich information about respondents' behavioral patterns and cognitive processes.

Lifelong Incremental Reinforcement Learning with Online Bayesian Inference

1 code implementation28 Jul 2020 Zhi Wang, Chunlin Chen, Daoyi Dong

In this paper, we propose LifeLong Incremental Reinforcement Learning (LLIRL), a new incremental algorithm for efficient lifelong adaptation to dynamic environments.

Bayesian Inference reinforcement-learning

ProcData: An R Package for Process Data Analysis

1 code implementation9 Jun 2020 Xueying Tang, Susu Zhang, Zhi Wang, Jingchen Liu, Zhiliang Ying

In addition, several response process generators and a real dataset of response processes of the climate control item in the 2012 Programme for International Student Assessment are included in the package.

AdaCompress: Adaptive Compression for Online Computer Vision Services

1 code implementation17 Sep 2019 Hongshan Li, Yu Guo, Zhi Wang, Shu-Tao Xia, Wenwu Zhu

Then we train the agent in a reinforcement learning way to adapt it for different deep learning cloud services that act as the {\em interactive training environment} and feeding a reward with comprehensive consideration of accuracy and data size.

Multimedia Image and Video Processing

Decentralized Federated Learning: A Segmented Gossip Approach

no code implementations21 Aug 2019 Chenghao Hu, Jingyan Jiang, Zhi Wang

The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data.

Federated Learning

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

no code implementations26 Jul 2019 Fei Yu, Jie Zhao, Yanjun Gong, Zhi Wang, Yuxi Li, Fan Yang, Bin Dong, Quanzheng Li, Li Zhang

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.

Transfer Learning

A Pvalue-guided Anomaly Detection Approach Combining Multiple Heterogeneous Log Parser Algorithms on IIoT Systems

no code implementations5 Jul 2019 Xueshuo Xie, Zhi Wang, Xuhang Xiao, Lei Yang, Shenwei Huang, Tao Li

In this paper, we use blockchain to prevent logs from being tampered with and propose a pvalue-guided anomaly detection approach.

Cryptography and Security

Load Balancing for Ultra-Dense Networks: A Deep Reinforcement Learning Based Approach

no code implementations3 Jun 2019 Yue Xu, Wenjun Xu, Zhi Wang, Jia-Ru Lin, Shuguang Cui

Third, this work proposes an offline-evaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way.


Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

4 code implementations21 Apr 2018 Xiao Ma, Liqin Zhao, Guan Huang, Zhi Wang, Zelin Hu, Xiaoqiang Zhu, Kun Gai

To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

Click-Through Rate Prediction Recommendation Systems +2

Still Hammerable and Exploitable: on the Effectiveness of Software-only Physical Kernel Isolation

no code implementations20 Feb 2018 Yueqiang Cheng, Zhi Zhang, Surya Nepal, Zhi Wang

The exploit is motivated by our key observation that the modern OSes have double-owned kernel buffers (e. g., video buffers) owned concurrently by the kernel and user domains.

Cryptography and Security

Stable Memory Allocation in the Hippocampus: Fundamental Limits and Neural Realization

no code implementations14 Dec 2016 Wenlong Mou, Zhi Wang, Li-Wei Wang

In Valiant's neuroidal model, the hippocampus was described as a randomly connected graph, the computation on which maps input to a set of activated neuroids with stable size.


Online Influence Maximization in Non-Stationary Social Networks

1 code implementation26 Apr 2016 Yixin Bao, Xiaoke Wang, Zhi Wang, Chuan Wu, Francis C. M. Lau

Nevertheless, the existing studies mostly investigate the problem on a one-off basis, assuming fixed known influence probabilities among users, or the knowledge of the exact social network topology.

Cannot find the paper you are looking for? You can Submit a new open access paper.