Search Results for author: Bo Yuan

Found 82 papers, 21 papers with code

Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation

1 code implementation22 Aug 2023 Zongyi Xu, Bo Yuan, Shanshan Zhao, Qianni Zhang, Xinbo Gao

The most recent methods of this kind measure the uncertainty of each pre-divided region for manual labelling but they suffer from redundant information and require additional efforts for region division.

Active Learning Point Cloud Segmentation +1

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework

1 code implementation29 May 2023 Yangyi Chen, Hongcheng Gao, Ganqu Cui, Lifan Yuan, Dehan Kong, Hanlu Wu, Ning Shi, Bo Yuan, Longtao Huang, Hui Xue, Zhiyuan Liu, Maosong Sun, Heng Ji

In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.

Adversarial Attack

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models

1 code implementation26 May 2023 Jinqi Xiao, Miao Yin, Yu Gong, Xiao Zang, Jian Ren, Bo Yuan

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks.

Model Compression

DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing

no code implementations9 May 2023 Songling Zhu, Ronghua Shang, Bo Yuan, Weitong Zhang, Yangyang Li, Licheng Jiao

This paper proposes a novel knowledge distillation algorithm based on dynamic entropy correction to reduce the gap by adjusting the student instead of the teacher.

Knowledge Distillation

Guided Focal Stack Refinement Network for Light Field Salient Object Detection

no code implementations9 May 2023 Bo Yuan, Yao Jiang, Keren Fu, Qijun Zhao

To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features.

object-detection Object Detection +1

Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy

1 code implementation1 May 2023 Yifan Shi, Kang Wei, Li Shen, Yingqi Liu, Xueqian Wang, Bo Yuan, DaCheng Tao

To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise.

Federated Learning

Improved dimension dependence of a proximal algorithm for sampling

no code implementations20 Feb 2023 Jiaojiao Fan, Bo Yuan, Yongxin Chen

For instance, for strongly log-concave distributions, our method has complexity bound $\tilde\mathcal{O}(\kappa d^{1/2})$ without warm start, better than the minimax bound for MALA.

Improving the Model Consistency of Decentralized Federated Learning

no code implementations8 Feb 2023 Yifan Shi, Li Shen, Kang Wei, Yan Sun, Bo Yuan, Xueqian Wang, DaCheng Tao

To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network.

Federated Learning

HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks

no code implementations20 Jan 2023 Jinqi Xiao, Chengming Zhang, Yu Gong, Miao Yin, Yang Sui, Lizhi Xiang, Dingwen Tao, Bo Yuan

By interpreting automatic rank selection from an architecture search perspective, we develop an end-to-end solution to determine the suitable layer-wise ranks in a differentiable and hardware-aware way.

Low-rank compression Model Compression

GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer

no code implementations13 Jan 2023 Miao Yin, Burak Uzkent, Yilin Shen, Hongxia Jin, Bo Yuan

We first develop a graph-based ranking for measuring the importance of attention heads, and the extracted importance information is further integrated to an optimization-based procedure to impose the heterogeneous structured sparsity patterns on the ViT models.

GUAP: Graph Universal Attack Through Adversarial Patching

no code implementations4 Jan 2023 Xiao Zang, Jie Chen, Bo Yuan

Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data.

Graph Attention Node Classification

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts

1 code implementation CVPR 2023 Han Liu, Yuhao Wu, Shixuan Zhai, Bo Yuan, Ning Zhang

The field of text-to-image generation has made remarkable strides in creating high-fidelity and photorealistic images.

Adversarial Text

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning

no code implementations17 Dec 2022 Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu

Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner.

reinforcement-learning Reinforcement Learning (RL)

Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

no code implementations12 Dec 2022 Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang, DaCheng Tao

Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics.

Autonomous Driving reinforcement-learning +2

Algorithm and Hardware Co-Design of Energy-Efficient LSTM Networks for Video Recognition with Hierarchical Tucker Tensor Decomposition

no code implementations5 Dec 2022 Yu Gong, Miao Yin, Lingyi Huang, Chunhua Deng, Yang Sui, Bo Yuan

Meanwhile, compared with the state-of-the-art tensor decomposed model-oriented hardware TIE, our proposed FDHT-LSTM architecture achieves better performance in throughput, area efficiency and energy efficiency, respectively on LSTM-Youtube workload.

Tensor Decomposition Video Recognition

CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness

no code implementations4 Dec 2022 Huy Phan, Miao Yin, Yang Sui, Bo Yuan, Saman Zonouz

Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks.

Adversarial Robustness Model Compression

RoChBert: Towards Robust BERT Fine-tuning for Chinese

1 code implementation28 Oct 2022 Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.

Data Augmentation Language Modelling

Text Editing as Imitation Game

1 code implementation21 Oct 2022 Ning Shi, Bin Tang, Bo Yuan, Longtao Huang, Yewen Pu, Jie Fu, Zhouhan Lin

Text editing, such as grammatical error correction, arises naturally from imperfect textual data.

Action Generation Grammatical Error Correction +1

Syntax-guided Localized Self-attention by Constituency Syntactic Distance

1 code implementation21 Oct 2022 Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang, Xinbing Wang, Zhouhan Lin

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data.

Machine Translation Translation

A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning

1 code implementation10 Oct 2022 Guozheng Ma, Zhen Wang, Zhecheng Yuan, Xueqian Wang, Bo Yuan, DaCheng Tao

Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains.

Data Augmentation reinforcement-learning +1

On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation

1 code implementation19 Sep 2022 Haimei Zhao, Jing Zhang, Zhuo Chen, Bo Yuan, DaCheng Tao

Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges.

Monocular Depth Estimation

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

no code implementations1 Sep 2022 Tiantian Zhang, Zichuan Lin, Yuxing Wang, Deheng Ye, Qiang Fu, Wei Yang, Xueqian Wang, Bin Liang, Bo Yuan, Xiu Li

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.

Bayesian Inference Knowledge Distillation +3

Robot Motion Planning as Video Prediction: A Spatio-Temporal Neural Network-based Motion Planner

no code implementations24 Aug 2022 Xiao Zang, Miao Yin, Lingyi Huang, Jingjin Yu, Saman Zonouz, Bo Yuan

Despite the current development in this direction, the efficient capture and processing of important sequential and spatial information, in a direct and simultaneous way, is still relatively under-explored.

Motion Planning Video Prediction

The least-used key selection method for information retrieval in large-scale Cloud-based service repositories

no code implementations16 Aug 2022 Jiayan Gu, Ashiq Anjum, Yan Wu, Lu Liu, John Panneerselvam, Yao Lu, Bo Yuan

The experimental results show that the proposed least-used key selection method improves the service retrieval efficiency significantly compared with the designated key selection method in the case of the unequal appearing probability of parameters in service retrieval requests under three indexing models.

Information Retrieval Management +1

SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

1 code implementation17 Jun 2022 Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang

Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well.

Autonomous Driving reinforcement-learning +2

Penalized Proximal Policy Optimization for Safe Reinforcement Learning

no code implementations24 May 2022 Linrui Zhang, Li Shen, Long Yang, Shixiang Chen, Bo Yuan, Xueqian Wang, DaCheng Tao

Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications.

reinforcement-learning Reinforcement Learning (RL) +1

Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation

no code implementations5 Apr 2022 Bo Yuan, Danpei Zhao, Shuai Shao, Zehuan Yuan, Changhu Wang

In two typical cross-domain semantic segmentation tasks, i. e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy.

Road Segmentation Unsupervised Domain Adaptation

BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic

no code implementations24 Jan 2022 Yulin Chen, Beishui Liao, Bruno Bentzen, Bo Yuan, Zelai Yao, Haixiao Chi, Dov Gabbay

In this paper, we propose a novel interpretable method, BTPK (Binary Talmudic Public Announcement Logic model), to help users understand the internal recognition logic of the name entity recognition tasks based on Talmudic Public Announcement Logic.

Decision Making Logical Reasoning +4

Hybrid intelligence for dynamic job-shop scheduling with deep reinforcement learning and attention mechanism

1 code implementation3 Jan 2022 Yunhui Zeng, Zijun Liao, Yuanzhi Dai, Rong Wang, Xiu Li, Bo Yuan

The dynamic job-shop scheduling problem (DJSP) is a class of scheduling tasks that specifically consider the inherent uncertainties such as changing order requirements and possible machine breakdown in realistic smart manufacturing settings.

Graph Representation Learning Job Shop Scheduling +2

A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning

no code implementations1 Jan 2022 Yuxing Wang, Tiantian Zhang, Yongzhe Chang, Bin Liang, Xueqian Wang, Bo Yuan

The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms.

Continuous Control Evolutionary Algorithms +3

An Open Source Representation for the NYS Electric Grid to Support Power Grid and Market Transition Studies

1 code implementation13 Dec 2021 M. Vivienne Liu, Bo Yuan, Zongjie Wang, Jeffrey A. Sward, K. Max Zhang, C. Lindsay Anderson

Under the increasing need to decarbonize energy systems, there is coupled acceleration in connection of distributed and intermittent renewable resources in power grids.

Probability Density Estimation Based Imitation Learning

no code implementations13 Dec 2021 Yang Liu, Yongzhe Chang, Shilei Jiang, Xueqian Wang, Bin Liang, Bo Yuan

In general, IL methods can be categorized into Behavioral Cloning (BC) and Inverse Reinforcement Learning (IRL).

Density Estimation Imitation Learning

CHIP: CHannel Independence-based Pruning for Compact Neural Networks

1 code implementation NeurIPS 2021 Yang Sui, Miao Yin, Yi Xie, Huy Phan, Saman Zonouz, Bo Yuan

Filter pruning has been widely used for neural network compression because of its enabled practical acceleration.

Neural Network Compression

Value Penalized Q-Learning for Recommender Systems

no code implementations15 Oct 2021 Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Xueqian Wang, Bo Yuan, Peilin Zhao

To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.

Offline RL Q-Learning +2

SPARK: co-exploring model SPArsity and low-RanKness for compact neural networks

no code implementations29 Sep 2021 Wanzhao Yang, Miao Yin, Yang Sui, Bo Yuan

Based on the observations and outcomes from our analysis, we then propose SPARK, a unified DNN compression framework that can simultaneously capture model SPArsity and low-RanKness in an efficient way.

Method for making multi-attribute decisions in wargames by combining intuitionistic fuzzy numbers with reinforcement learning

no code implementations6 Sep 2021 Yuxiang Sun, Bo Yuan, Yufan Xue, Jiawei Zhou, XiaoYu Zhang, Xianzhong Zhou

Researchers are increasingly focusing on intelligent games as a hot research area. The article proposes an algorithm that combines the multi-attribute management and reinforcement learning methods, and that combined their effect on wargaming, it solves the problem of the agent's low rate of winning against specific rules and its inability to quickly converge during intelligent wargame training. At the same time, this paper studied a multi-attribute decision making and reinforcement learning algorithm in a wargame simulation environment, and obtained data on red and blue conflict. Calculate the weight of each attribute based on the intuitionistic fuzzy number weight calculations.

Decision Making Management +2

Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation

1 code implementation1 Sep 2021 Tiantian Zhang, Xueqian Wang, Bin Liang, Bo Yuan

In this paper, we present IQ, i. e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning.

General Reinforcement Learning Knowledge Distillation +5

Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework

no code implementations CVPR 2021 Miao Yin, Yang Sui, Siyu Liao, Bo Yuan

Notably, on CIFAR-100, with 2. 3X and 2. 4X compression ratios, our models have 1. 96% and 2. 21% higher top-1 accuracy than the original ResNet-20 and ResNet-32, respectively.

Image Classification Model Compression +2

Boosting Offline Reinforcement Learning with Residual Generative Modeling

no code implementations19 Jun 2021 Hua Wei, Deheng Ye, Zhao Liu, Hao Wu, Bo Yuan, Qiang Fu, Wei Yang, Zhenhui Li

While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.

Offline RL Q-Learning +2

Optimization of Service Addition in Multilevel Index Model for Edge Computing

no code implementations8 Jun 2021 Jiayan Gu, Yan Wu, Ashiq Anjum, John Panneerselvam, Yao Lu, Bo Yuan

With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume.

Edge-computing Retrieval

Multi-view Clustering with Deep Matrix Factorization and Global Graph Refinement

no code implementations1 May 2021 Chen Zhang, Siwei Wang, Wenxuan Tu, Pei Zhang, Xinwang Liu, Changwang Zhang, Bo Yuan

Multi-view clustering is an important yet challenging task in machine learning and data mining community.


Inference of cell dynamics on perturbation data using adjoint sensitivity

1 code implementation13 Apr 2021 Weiqi Ji, Bo Yuan, Ciyue Shen, Aviv Regev, Chris Sander, Sili Deng

While there is no analogous ground truth for real life biological systems, this work demonstrates the ability to construct and parameterize a considerable diversity of network models with high predictive ability.

Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure

no code implementations CVPR 2021 Miao Yin, Siyu Liao, Xiao-Yang Liu, Xiaodong Wang, Bo Yuan

Although various prior works have been proposed to reduce the RNN model sizes, executing RNN models in resource-restricted environments is still a very challenging problem.

Tensor Decomposition Video Recognition

Noise Injection-based Regularization for Point Cloud Processing

no code implementations28 Mar 2021 Xiao Zang, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs.

Data Augmentation Semantic Segmentation

Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding

no code implementations8 Feb 2021 Siyu Liao, Chunhua Deng, Miao Yin, Bo Yuan

Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance.

Vocal Bursts Intensity Prediction

NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection

no code implementations8 Jan 2021 Liang Xu, Liying Zheng, Weijun Li, Zhenbo Chen, Weishun Song, Yue Deng, Yongzhe Chang, Jing Xiao, Bo Yuan

In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs).

Anomaly Detection Time Series +1

How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?

no code implementations30 Dec 2020 Li Zhong, Zhen Fang, Feng Liu, Jie Lu, Bo Yuan, Guangquan Zhang

Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy.

Unsupervised Domain Adaptation

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

no code implementations25 Nov 2020 Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang

Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.

Towards Playing Full MOBA Games with Deep Reinforcement Learning

no code implementations NeurIPS 2020 Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.

Dota 2 reinforcement-learning +1

Learning from a Complementary-label Source Domain: Theory and Algorithms

1 code implementation4 Aug 2020 Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan, Guangquan Zhang, Jie Lu

We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA).

Unsupervised Domain Adaptation

Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

1 code implementation29 Jul 2020 Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan, Guangquan Zhang, Jie Lu

To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA).

Unsupervised Domain Adaptation

Local Causal Structure Learning and its Discovery Between Type 2 Diabetes and Bone Mineral Density

no code implementations27 Jun 2020 Wei Wang, Gangqiang Hu, Bo Yuan, Shandong Ye, Chao Chen, YaYun Cui, Xi Zhang, Liting Qian

To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.

Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation

no code implementations23 Jun 2020 Li Zhong, Zhen Fang, Feng Liu, Bo Yuan, Guangquan Zhang, Jie Lu

To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data.

Domain Adaptation Object Recognition

Enabling Fast and Universal Audio Adversarial Attack Using Generative Model

no code implementations26 Apr 2020 Yi Xie, Zhuohang Li, Cong Shi, Jian Liu, Yingying Chen, Bo Yuan

These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e. g., playing unnoticeable adversarial perturbations along with user's streaming input).

Adversarial Attack

PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices

no code implementations23 Apr 2020 Chunhua Deng, Siyu Liao, Yi Xie, Keshab K. Parhi, Xuehai Qian, Bo Yuan

On the other hand, the recent structured matrix-based approach (i. e., CirCNN) is limited by the relatively complex arithmetic computation (i. e., FFT), less flexible compression ratio, and its inability to fully utilize input sparsity.

Model Compression

Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems

no code implementations4 Mar 2020 Yi Xie, Cong Shi, Zhuohang Li, Jian Liu, Yingying Chen, Bo Yuan

As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services.

Adversarial Attack Room Impulse Response (RIR) +1

Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models

1 code implementation12 Feb 2020 Xiao Zang, Yi Xie, Jie Chen, Bo Yuan

Worse, the bad actors found for one graph model severely compromise other models as well.

Graph Learning

Embedding Compression with Isotropic Iterative Quantization

no code implementations11 Jan 2020 Siyu Liao, Jie Chen, Yanzhi Wang, Qinru Qiu, Bo Yuan

Continuous representation of words is a standard component in deep learning-based NLP models.

Image Retrieval Quantization +1

CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator

no code implementations16 Dec 2019 Huy Phan, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.

Adversarial Attack

They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimization

no code implementations16 Sep 2019 Rayan Mosli, Matthew Wright, Bo Yuan, Yin Pan

In this paper, we present AdversarialPSO, a black-box attack that uses fewer queries to create adversarial examples with high success rates.

Image Classification

A Critical Note on the Evaluation of Clustering Algorithms

no code implementations10 Aug 2019 Tiantian Zhang, Li Zhong, Bo Yuan

Experimental evaluation is a major research methodology for investigating clustering algorithms and many other machine learning algorithms.

Clustering Dimensionality Reduction

CircConv: A Structured Convolution with Low Complexity

no code implementations28 Feb 2019 Siyu Liao, Zhe Li, Liang Zhao, Qinru Qiu, Yanzhi Wang, Bo Yuan

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.

Representation Learning for Heterogeneous Information Networks via Embedding Events

1 code implementation29 Jan 2019 Guoji Fu, Bo Yuan, Qiqi Duan, Xin Yao

Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space.

Link Prediction Node Classification +1

SGAD: Soft-Guided Adaptively-Dropped Neural Network

no code implementations4 Jul 2018 Zhisheng Wang, Fangxuan Sun, Jun Lin, Zhongfeng Wang, Bo Yuan

Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper.

Model Compression

Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing

no code implementations10 May 2018 Zhe Li, Ji Li, Ao Ren, Caiwen Ding, Jeffrey Draper, Qinru Qiu, Bo Yuan, Yanzhi Wang

Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications.

Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICs

no code implementations28 Mar 2018 Caiwen Ding, Ao Ren, Geng Yuan, Xiaolong Ma, Jiayu Li, Ning Liu, Bo Yuan, Yanzhi Wang

For FPGA implementations on deep convolutional neural networks (DCNNs), we achieve at least 152X and 72X improvement in performance and energy efficiency, respectively using the SWM-based framework, compared with the baseline of IBM TrueNorth processor under same accuracy constraints using the data set of MNIST, SVHN, and CIFAR-10.

C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs

no code implementations14 Mar 2018 Shuo Wang, Zhe Li, Caiwen Ding, Bo Yuan, Yanzhi Wang, Qinru Qiu, Yun Liang

The previous work proposes to use a pruning based compression technique to reduce the model size and thus speedups the inference on FPGAs.

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

no code implementations ICML 2017 Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.

SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing

no code implementations18 Nov 2016 Ao Ren, Ji Li, Zhe Li, Caiwen Ding, Xuehai Qian, Qinru Qiu, Bo Yuan, Yanzhi Wang

Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability and ultra-low hardware footprint.

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