Yongdao Zhou

Prof. Dr. Yongdao Zhou

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
27 September 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SYSiyu Yi
Siyu Yi
WJWei Ju
Wei Ju
YQYifang Qin
Yifang Qin
XLXiao Luo
Xiao Luo
LLLuchen Liu
Luchen Liu
MZMing Zhang
Ming Zhang
Graph clustering, which learns the node representations for effective cluster assignments, is a fundamental yet challenging task in data analysis and has received considerable attention accompanied by graph neural networks (GNNs) in recent years. However, most existing methods overlook the inherent relational information among the nonindependent and nonidentically distributed nodes in a graph. Due to the lack of exploration of relational attributes, the semantic information of the graph-structured data fails to be fully exploited which leads to poor clustering performance. In this article, we propose a novel self-supervised deep graph clustering method named relational redundancy-free graph clustering (R $^2$ FGC) to tackle the problem. It extracts the attribute-and structure-level relational information from both global and local views based on an autoencoder (AE) and a graph AE (GAE). To obtain effective representations of the semantic information, we preserve the consistent relationship among augmented nodes, whereas the redundant relationship is further reduced for learning discriminative embeddings. In addition, a simple yet valid strategy is used to alleviate the oversmoothing issue. Extensive experiments are performed on widely used benchmark datasets to validate the superiority of our R $^2$ FGC over state-of-the-art baselines. Our codes are available at https://github.com/yisiyu95/R2FGC.

7 September 2023 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
SYSi-Yu Yi
Si-Yu Yi
ZMZhengyang Mao
Zhengyang Mao
WJWei Ju
Wei Ju
Yongdao ZhouYongdao Zhou
Yongdao Zhou
LLLuchen Liu
Luchen Liu
MZMing Zhang
Ming Zhang
Graph classification, aiming at learning the graph-level representations for effective class assignments, has received outstanding achievements, which heavily relies on high-quality datasets that have balanced class distribution. In fact, most real-world graph data naturally presents a long-tailed form, where the head classes occupy much more samples than the tail classes, it thus is essential to study the graph-level classification over long-tailed data while still remaining largely unexplored. However, most existing long-tailed learning methods in visions fail to jointly optimize the representation learning and classifier training, as well as neglect the mining of the hard-to-classify classes. Directly applying existing methods to graphs may lead to sub-optimal performance, since the model trained on graphs would be more sensitive to the long-tailed distribution due to the complex topological characteristics. Hence, in this paper, we propose a novel long-tailed graph-level classification framework via Co llaborative M ulti- e xpert Learning (CoMe) to tackle the problem. To equilibrate the contributions of head and tail classes, we first develop balanced contrastive learning from the view of representation learning, and then design an individual-expert classifier training based on hard class mining. In addition, we execute gated fusion and disentangled knowledge distillation among the multiple experts to promote the collaboration in a multi-expert framework. Comprehensive experiments are performed on seven widely-used benchmark datasets to demonstrate the superiority of our method CoMe over state-of-the-art baselines.

24 July 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
MZMei Zhang
Mei Zhang
Yongdao ZhouYongdao Zhou
Yongdao Zhou
ZZZheng Zhou
Zheng Zhou
AZAijun Zhang
Aijun Zhang
Subsampling or subdata selection is a useful approach in large-scale statistical learning. Most existing studies focus on model-based subsampling methods which significantly depend on the model assumption. In this article, we consider the model-free subsampling strategy for generating subdata from the original full data. In order to measure the goodness of representation of a subdata with respect to the original data, we propose a criterion, generalized empirical $F$ -discrepancy (GEFD), and study its theoretical properties in connection with the classical generalized $\ell _{2}$ -discrepancy in the theory of uniform designs. These properties allow us to develop a kind of low-GEFD data-driven subsampling method based on the existing uniform designs. By simulation examples and a real case study, we show that the proposed subsampling method is superior to the random sampling method. Moreover, our method keeps robust under diverse model specifications while other popular model-based subsampling methods are under-performing. In practice, such a model-free property is more appealing than the model-based subsampling methods, where the latter may have poor performance when the model is misspecified, as demonstrated in our simulation studies. In addition, our method is orders of magnitude faster than other model-free subsampling methods, which makes it more applicable for subsampling of Big Data.

1 May 2020 in Journal of Statistical Planning and Inference
Verified
Journal Article
Closed access
XZXue-Ru Zhang
Xue-Ru Zhang
MLMin-Qian Liu
Min-Qian Liu
Yongdao ZhouYongdao Zhou
Yongdao Zhou

1 December 2022 in Statistics and Computing
Verified
Journal Article
Closed access
PDF file
SYSi-Yu Yi
Si-Yu Yi
Yongdao ZhouYongdao Zhou
Yongdao Zhou

1 September 2018 in Statistics & Probability Letters
Verified
Journal Article
Closed access
SYSi-Yu Yi
Si-Yu Yi
Yongdao ZhouYongdao Zhou
Yongdao Zhou