Alert button
Picture for Zhonghai Wu

Zhonghai Wu

Alert button

SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image

Jun 25, 2023
Luyuan Xie, Cong Li, Zirui Wang, Xin Zhang, Boyan Chen, Qingni Shen, Zhonghai Wu

Figure 1 for SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image
Figure 2 for SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image
Figure 3 for SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image
Figure 4 for SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image

The rapid identification and accurate diagnosis of breast cancer, known as the killer of women, have become greatly significant for those patients. Numerous breast cancer histopathological image classification methods have been proposed. But they still suffer from two problems. (1) These methods can only hand high-resolution (HR) images. However, the low-resolution (LR) images are often collected by the digital slide scanner with limited hardware conditions. Compared with HR images, LR images often lose some key features like texture, which deeply affects the accuracy of diagnosis. (2) The existing methods have fixed receptive fields, so they can not extract and fuse multi-scale features well for images with different magnification factors. To fill these gaps, we present a \textbf{S}ingle \textbf{H}istopathological \textbf{I}mage \textbf{S}uper-\textbf{R}esolution \textbf{C}lassification network (SHISRCNet), which consists of two modules: Super-Resolution (SR) and Classification (CF) modules. SR module reconstructs LR images into SR ones. CF module extracts and fuses the multi-scale features of SR images for classification. In the training stage, we introduce HR images into the CF module to enhance SHISRCNet's performance. Finally, through the joint training of these two modules, super-resolution and classified of LR images are integrated into our model. The experimental results demonstrate that the effects of our method are close to the SOTA methods with taking HR images as inputs.

* Accepted by MICCAI 2023 
Viaarxiv icon

NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning

Mar 03, 2023
Shengfang Zhai, Qingni Shen, Xiaoyi Chen, Weilong Wang, Cong Li, Yuejian Fang, Zhonghai Wu

Figure 1 for NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
Figure 2 for NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
Figure 3 for NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
Figure 4 for NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the poisoned dataset. In the field of text, however, existing works do not provide sufficient defense against backdoor attacks. In this paper, we propose a Noise-augmented Contrastive Learning (NCL) framework to defend against textual backdoor attacks when training models with untrustworthy data. With the aim of mitigating the mapping between triggers and the target label, we add appropriate noise perturbing possible backdoor triggers, augment the training dataset, and then pull homology samples in the feature space utilizing contrastive learning objective. Experiments demonstrate the effectiveness of our method in defending three types of textual backdoor attacks, outperforming the prior works.

* 6 pages, 5 figures. To appear in ICASSP 2023 
Viaarxiv icon

TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene

Oct 05, 2022
Luyuan Xie, Yan Zhong, Lin Yang, Zhaoyu Yan, Zhonghai Wu, Junjie Wang

Figure 1 for TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene
Figure 2 for TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene
Figure 3 for TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene
Figure 4 for TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene

Convolution neural networks (CNNs) have good performance in low-complexity classification tasks such as acoustic scene classifications (ASCs). However, there are few studies on the relationship between the length of target speech and the size of the convolution kernels. In this paper, we combine Selective Kernel Network with Temporal-Convolution (TC-SKNet) to adjust the receptive field of convolution kernels to solve the problem of variable length of target voice while keeping low-complexity. GridMask is a data augmentation strategy by masking part of the raw data or feature area. It can enhance the generalization of the model as the role of dropout. In our experiments, the performance gain brought by GridMask is stronger than spectrum augmentation in ASCs. Finally, we adopt AutoML to search best structure of TC-SKNet and hyperparameters of GridMask for improving the classification performance. As a result, a peak accuracy of 59.87% TC-SKNet is equivalent to that of SOTA, but the parameters only use 20.9 K.

* Accepted to APSIPA ASC 2022 
Viaarxiv icon

Kallima: A Clean-label Framework for Textual Backdoor Attacks

Jun 03, 2022
Xiaoyi Chen, Yinpeng Dong, Zeyu Sun, Shengfang Zhai, Qingni Shen, Zhonghai Wu

Figure 1 for Kallima: A Clean-label Framework for Textual Backdoor Attacks
Figure 2 for Kallima: A Clean-label Framework for Textual Backdoor Attacks
Figure 3 for Kallima: A Clean-label Framework for Textual Backdoor Attacks
Figure 4 for Kallima: A Clean-label Framework for Textual Backdoor Attacks

Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly inject a small number of poisoned samples into the training dataset with the labels changed to the target one. Such mislabeled samples would raise suspicion upon human inspection, potentially revealing the attack. To improve the stealthiness of textual backdoor attacks, we propose the first clean-label framework Kallima for synthesizing mimesis-style backdoor samples to develop insidious textual backdoor attacks. We modify inputs belonging to the target class with adversarial perturbations, making the model rely more on the backdoor trigger. Our framework is compatible with most existing backdoor triggers. The experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method.

Viaarxiv icon

A Vertical Federated Learning Framework for Horizontally Partitioned Labels

Jun 18, 2021
Wensheng Xia, Ying Li, Lan Zhang, Zhonghai Wu, Xiaoyong Yuan

Figure 1 for A Vertical Federated Learning Framework for Horizontally Partitioned Labels
Figure 2 for A Vertical Federated Learning Framework for Horizontally Partitioned Labels
Figure 3 for A Vertical Federated Learning Framework for Horizontally Partitioned Labels
Figure 4 for A Vertical Federated Learning Framework for Horizontally Partitioned Labels

Vertical federated learning is a collaborative machine learning framework to train deep leaning models on vertically partitioned data with privacy-preservation. It attracts much attention both from academia and industry. Unfortunately, applying most existing vertical federated learning methods in real-world applications still faces two daunting challenges. First, most existing vertical federated learning methods have a strong assumption that at least one party holds the complete set of labels of all data samples, while this assumption is not satisfied in many practical scenarios, where labels are horizontally partitioned and the parties only hold partial labels. Existing vertical federated learning methods can only utilize partial labels, which may lead to inadequate model update in end-to-end backpropagation. Second, computational and communication resources vary in parties. Some parties with limited computational and communication resources will become the stragglers and slow down the convergence of training. Such straggler problem will be exaggerated in the scenarios of horizontally partitioned labels in vertical federated learning. To address these challenges, we propose a novel vertical federated learning framework named Cascade Vertical Federated Learning (CVFL) to fully utilize all horizontally partitioned labels to train neural networks with privacy-preservation. To mitigate the straggler problem, we design a novel optimization objective which can increase straggler's contribution to the trained models. We conduct a series of qualitative experiments to rigorously verify the effectiveness of CVFL. It is demonstrated that CVFL can achieve comparable performance (e.g., accuracy for classification tasks) with centralized training. The new optimization objective can further mitigate the straggler problem comparing with only using the asynchronous aggregation mechanism during training.

* 10 pages, 6 figures 
Viaarxiv icon

Relation-Aware Neighborhood Matching Model for Entity Alignment

Dec 15, 2020
Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yingpeng Du

Figure 1 for Relation-Aware Neighborhood Matching Model for Entity Alignment
Figure 2 for Relation-Aware Neighborhood Matching Model for Entity Alignment
Figure 3 for Relation-Aware Neighborhood Matching Model for Entity Alignment
Figure 4 for Relation-Aware Neighborhood Matching Model for Entity Alignment

Entity alignment which aims at linking entities with the same meaning from different knowledge graphs (KGs) is a vital step for knowledge fusion. Existing research focused on learning embeddings of entities by utilizing structural information of KGs for entity alignment. These methods can aggregate information from neighboring nodes but may also bring noise from neighbors. Most recently, several researchers attempted to compare neighboring nodes in pairs to enhance the entity alignment. However, they ignored the relations between entities which are also important for neighborhood matching. In addition, existing methods paid less attention to the positive interactions between the entity alignment and the relation alignment. To deal with these issues, we propose a novel Relation-aware Neighborhood Matching model named RNM for entity alignment. Specifically, we propose to utilize the neighborhood matching to enhance the entity alignment. Besides comparing neighbor nodes when matching neighborhood, we also try to explore useful information from the connected relations. Moreover, an iterative framework is designed to leverage the positive interactions between the entity alignment and the relation alignment in a semi-supervised manner. Experimental results on three real-world datasets demonstrate that the proposed model RNM performs better than state-of-the-art methods.

* AAAI 2021 
Viaarxiv icon

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

Sep 26, 2019
Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang Song, Tao Zhang

Figure 1 for Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
Figure 2 for Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
Figure 3 for Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
Figure 4 for Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

Incompleteness is a common problem for existing knowledge graphs (KGs), and the completion of KG which aims to predict links between entities is challenging. Most existing KG completion methods only consider the direct relation between nodes and ignore the relation paths which contain useful information for link prediction. Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning. In addition, these path-based models always ignore nonlinear contributions of path features for link prediction. To solve these problems, we propose a novel KG completion method named OPTransE. Instead of embedding both entities of a relation into the same latent space as in previous methods, we project the head entity and the tail entity of each relation into different spaces to guarantee the order of relations in the path. Meanwhile, we adopt a pooling strategy to extract nonlinear and complex features of different paths to further improve the performance of link prediction. Experimental results on two benchmark datasets show that the proposed model OPTransE performs better than state-of-the-art methods.

Viaarxiv icon

An influence-based fast preceding questionnaire model for elderly assessments

Nov 22, 2017
Tong Mo, Rong Zhang, Weiping Li, Jingbo Zhang, Zhonghai Wu, Wei Tan

Figure 1 for An influence-based fast preceding questionnaire model for elderly assessments
Figure 2 for An influence-based fast preceding questionnaire model for elderly assessments
Figure 3 for An influence-based fast preceding questionnaire model for elderly assessments
Figure 4 for An influence-based fast preceding questionnaire model for elderly assessments

To improve the efficiency of elderly assessments, an influence-based fast preceding questionnaire model (FPQM) is proposed. Compared with traditional assessments, the FPQM optimizes questionnaires by reordering their attributes. The values of low-ranking attributes can be predicted by the values of the high-ranking attributes. Therefore, the number of attributes can be reduced without redesigning the questionnaires. A new function for calculating the influence of the attributes is proposed based on probability theory. Reordering and reducing algorithms are given based on the attributes' influences. The model is verified through a practical application. The practice in an elderly-care company shows that the FPQM can reduce the number of attributes by 90.56% with a prediction accuracy of 98.39%. Compared with other methods, such as the Expert Knowledge, Rough Set and C4.5 methods, the FPQM achieves the best performance. In addition, the FPQM can also be applied to other questionnaires.

* Accepted by the journal "Intelligent Data Analysis" 
Viaarxiv icon