Weiwei Liu

Weiwei Liu

Auto-generated profile, based on publicly available information

Weiwei Liu

School of Computer Science, Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 October 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WLWeiwei Liu
Weiwei Liu
HWHaobo Wang
Haobo Wang
XSXiaobo Shen
Xiaobo Shen
ITIvor Tsang
Ivor Tsang
Exabytes of data are generated daily by humans, leading to the growing needs for new efforts in dealing with the grand challenges for multi-label learning brought by big data. For example, extreme multi-label classification is an active and rapidly growing research area that deals with classification tasks with extremely large number of classes or labels; utilizing massive data with limited supervision to build a multi-label classification model becomes valuable for practical applications, etc. Besides these, there are tremendous efforts on how to harvest the strong learning capability of deep learning to better capture the label dependencies in multi-label learning, which is the key for deep learning to address real-world classification tasks. However, it is noted that there have been a lack of systemic studies that focus explicitly on analyzing the emerging trends and new challenges of multi-label learning in the era of big data. It is imperative to call for a comprehensive survey to fulfil this mission and delineate future research directions and new applications.

18 January 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WLWeiwei Liu
Weiwei Liu
DXDonna Xu
Donna Xu
ITIvor Tsang
Ivor Tsang
Wenjie ZhangWenjie Zhang
Wenjie Zhang
Multi-output learning with the task of simultaneously predicting multiple outputs for an input has increasingly attracted interest from researchers due to its wide application. The k nearest neighbor (kNN) algorithm is one of the most popular frameworks for handling multi-output problems. The performance of kNN depends crucially on the metric used to compute the distance between different instances. However, our experiment results show that the existing advanced metric learning technique cannot provide an appropriate distance metric for multi-output tasks. This paper systematically studies how to learn an appropriate distance metric for multi-output problems. In particular, we present a novel large margin metric learning paradigm for multi-output tasks, which projects both the input and output into the same embedding space and then learns a distance metric to discover output dependency such that instances with very different multiple outputs will be moved far away. Several strategies are then proposed to speed up the training and testing time. Moreover, we study the generalization error bound of our method, which shows that our method is able to tighten the excess risk bounds. Experiments on three multi-output learning tasks (multi-label classification, multi-target regression, and multi-concept retrieval) validate the effectiveness and scalability of the proposed method.

7 November 2017 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XSXiaobo Shen
Xiaobo Shen
WLWeiwei Liu
Weiwei Liu
ITIvor Tsang
Ivor Tsang
QSQuansen Sun
Quansen Sun
YOYew-Soon Ong
Yew-Soon Ong
Embedding methods have shown promising performance in multilabel prediction, as they are able to discover the label dependence. However, most methods ignore the correlations between the input and output, such that their learned embeddings are not well aligned, which leads to degradation in prediction performance. This paper presents a formulation for multilabel learning, from the perspective of cross-view learning, that explores the correlations between the input and the output. The proposed method, called Co-Embedding (CoE), jointly learns a semantic common subspace and view-specific mappings within one framework. The semantic similarity structure among the embeddings is further preserved, ensuring that close embeddings share similar labels. Additionally, CoE conducts multilabel prediction through the cross-view k nearest neighborhood (kNN) search among the learned embeddings, which significantly reduces computational costs compared with conventional decoding schemes. A hashing-based model, i.e., Co-Hashing (CoH), is further proposed. CoH is based on CoE, and imposes the binary constraint on continuous latent embeddings. CoH aims to generate compact binary representations to improve the prediction efficiency by benefiting from the efficient kNN search of multiple labels in the Hamming space. Extensive experiments on various real-world data sets demonstrate the superiority of the proposed methods over the state of the arts in terms of both prediction accuracy and efficiency.

1 October 2021 in Neural Networks
Verified
Journal Article
Closed access
CLChuang Liu
Chuang Liu
Jia WUJia WU
Jia WU
WLWeiwei Liu
Weiwei Liu
WHWenbin Hu
Wenbin Hu

1 August 2023
Verified
Conference Paper
Open access
PDF file
HWHaobo Wang
Haobo Wang
SYShisong Yang
Shisong Yang
GLGengyu Lyu
Gengyu Lyu
WLWeiwei Liu
Weiwei Liu
THTianlei Hu
Tianlei Hu
GCGang Chen
Gang Chen
In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels. Recently, graph-based methods, which demonstrate a good ability to estimate accurate confidence scores from candidate labels, have been prevalent to deal with PML problems. However, we observe that existing graph-based PML methods typically adopt linear multi-label classifiers and thus fail to achieve superior performance. In this work, we attempt to remove several obstacles for extending them to deep models and propose a novel deep Partial multi-Label model with grAph-disambIguatioN (PLAIN). Specifically, we introduce the instance-level and label-level similarities to recover label confidences as well as exploit label dependencies. At each training epoch, labels are propagated on the instance and label graphs to produce relatively accurate pseudo-labels; then, we train the deep model to fit the numerical labels. Moreover, we provide a careful analysis of the risk functions to guarantee the robustness of the proposed model. Extensive experiments on various synthetic datasets and three real-world PML datasets demonstrate that PLAIN achieves significantly superior results to state-of-the-art methods.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
BLBoqi Li
Boqi Li
WLWeiwei Liu
Weiwei Liu
Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works have shown that a robust model well-trained by AT exhibits a remarkable robustness disparity among classes, and propose various methods to obtain consistent robust accuracy across classes. Unfortunately, these methods sacrifice a good deal of the average robust accuracy. Accordingly, this paper proposes a novel framework of worst-class adversarial training and leverages no-regret dynamics to solve this problem. Our goal is to obtain a classifier with great performance on worst-class and sacrifice just a little average robust accuracy at the same time. We then rigorously analyze the theoretical properties of our proposed algorithm, and the generalization error bound in terms of the worst-class robust risk. Furthermore, we propose a measurement to evaluate the proposed method in terms of both the average and worst-class accuracies. Experiments on various datasets and networks show that our proposed method outperforms the state-of-the-art approaches.