Zhao Zhang

Zhao Zhang

Auto-generated profile, based on publicly available information

Zhao Zhang

School of Computer Science and Engineering, Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
21 October 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
ZSZezhi Shao
Zezhi Shao
FWFei Wang
Fei Wang
YXYongjun Xu
Yongjun Xu
WWWei Wei
Wei Wei
CYChengqing Yu
Chengqing Yu
XCXueqi Cheng
Xueqi Cheng
Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently. However, we often observe inconsistent or seemingly contradictory performance findings across different studies. This hinders our understanding of the merits of different approaches and slows down progress. We address the need for means of assessing MTS forecasting proposals reliably and fairly, in turn enabling better exploitation of MTS as seen in different applications. Specifically, we first propose BasicTS+, a benchmark designed to enable fair, comprehensive, and reproducible comparison of MTS forecasting solutions. BasicTS+ establishes a unified training pipeline and reasonable settings, enabling an unbiased evaluation. Second, we identify the heterogeneity across different MTS as an important consideration and enable classification of MTS based on their temporal and spatial characteristics. Disregarding this heterogeneity is a prime reason for difficulties in selecting the most promising technical directions. Third, we apply BasicTS+ along with rich datasets to assess the capabilities of more than 30 MTS forecasting solutions. This provides readers with an overall picture of the cutting-edge research on MTS forecasting.

13 May 2025 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
CYChengqing Yu
Chengqing Yu
FWFei Wang
Fei Wang
ZSZezhi Shao
Zezhi Shao
TQTangwen Qian
Tangwen Qian
ZZZhao Zhang
Zhao Zhang
YXYongjun Xu
Yongjun Xu
Spatial-Temporal Graph Neural Networks (STGNNs) have been widely utilized in multivariate time series forecasting (MTSF), but they rely on the assumption of data completeness. In practice, due to factors such as natural disaster, STGNNs frequently encounter the challenge of missing data resulting from numerous malfunctioning data collectors. In this case, on the one hand, due to the presence of missing values, STGNNs easily generate incorrect spatial correlations, leading to the performance degradation. On the other hand, STGNNs require separate training of models for different missing rates, limiting their robustness. To address these challenges, we first propose two important components (interpolation attention and adaptive graph convolution), which utilize normal values to recover missing values into reliable representations and reconstruct spatial correlations. Then, we replace the fully connected layers in simple recursive units with these two components and propose Graph Interpolation Attention Recursive Network (GinAR), aiming to recursively correct spatial correlations and achieve end-to-end MTSF with missing values. Finally, we use data with different missing rates as positive and negative data pairs. By employing contrastive learning to train GinAR, we propose GinAR+ and enhance its robustness to data with different missing rates. Experiments validate the superiority of GinAR+ and our motivation.

9 February 2024 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
WCWei Chen
Wei Chen
YWYiqing Wu
Yiqing Wu
ZZZhao Zhang
Zhao Zhang
FZFuzhen Zhuang
Fuzhen Zhuang
ZHZhongshi He
Zhongshi He
FXFeng Xia
Feng Xia
The emergence of Graph Neural Networks (GNNs) has greatly advanced the development of recommendation systems. Recently, many researchers have leveraged GNN-based models to learn fair representations for users and items. However, current GNN-based models suffer from biased user–item interaction data, which negatively impacts recommendation fairness. Although there have been several studies employing adversarial learning to mitigate this issue in recommendation systems, they mostly focus on modifying the model training approach with fairness regularization and neglect direct intervention of biased interaction. In contrast to these models, this article introduces a novel perspective by directly intervening in observed interactions to generate a counterfactual graph (called FairGap) that is not influenced by sensitive node attributes, enabling us to learn fair representations for users and items easily. We design FairGap to answer the key counterfactual question: “Would interactions with an item remain unchanged if a user’s sensitive attributes were concealed?”. We also provide theoretical proofs to show that our learning strategy via the counterfactual graph is unbiased in expectation. Moreover, we propose a fairness-enhancing mechanism to continuously improve user fairness in the graph-based recommendation. Extensive experimental results against state-of-the-art competitors and base models on three real-world datasets validate the effectiveness of our proposed model.

24 August 2024
Verified
Conference Paper
Open access
CYChengqing Yu
Chengqing Yu
FWFei Wang
Fei Wang
ZSZezhi Shao
Zezhi Shao
TQTangwen Qian
Tangwen Qian
ZZZhao Zhang
Zhao Zhang
YXYongjun Xu
Yongjun Xu
Multivariate time series forecasting (MTSF) is crucial for decision-making to precisely forecast the future values/trends, based on the complex relationships identified from historical observations of multiple sequences. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have gradually become the theme of MTSF model as their powerful capability in mining spatial-temporal dependencies, but almost of them heavily rely on the assumption of historical data integrity. In reality, due to factors such as data collector failures and time-consuming repairment, it is extremely challenging to collect the whole historical observations without missing any variable. In this case, STGNNs can only utilize a subset of normal variables and easily suffer from the incorrect spatial-temporal dependency modeling issue, resulting in the degradation of their forecasting performance. To address the problem, in this paper, we propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to precisely model the spatial-temporal dependencies over the limited collected data for forecasting. In GinAR, it consists of two key components, that is, interpolation attention and adaptive graph convolution to take place of the fully connected layer of simple recursive units, and thus are capable of recovering all missing variables and reconstructing the correct spatial-temporal dependencies for recursively modeling of multivariate time series data, respectively. Extensive experiments conducted on five real-world datasets demonstrate that GinAR outperforms 11 SOTA baselines, and even when 90% of variables are missing, it can still accurately predict the future values of all variables.

23 November 2022 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
ZSZezhi Shao
Zezhi Shao
YXYongjun Xu
Yongjun Xu
WWWei Wei
Wei Wei
FWFei Wang
Fei Wang
ZZZhao Zhang
Zhao Zhang
FZFeida Zhu
Feida Zhu
In recent years, graph neural networks (GNNs)-based methods have been widely adopted for heterogeneous graph (HG) embedding, due to their power in effectively encoding rich information from a HG into the low-dimensional node embeddings. However, previous works usually easily fail to fully leverage the inherent heterogeneity and rich semantics contained in the complex local structures of HGs. On the one hand, most of the existing methods either inadequately model the local structure under specific semantics, or neglect the heterogeneity when aggregating information from the local structure. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain node embeddings with versatility. To address the problem, we propose a Heterogeneous Graph Neural Network for HG embedding within a Multi-View representation learning framework (named MV-HetGNN), which consists of a view-specific ego graph encoder and auto multi-view fusion layer. MV-HetGNN thoroughly learns complex heterogeneity and semantics in the local structure to generate comprehensive and versatile node representations for HGs. Extensive experiments on three real-world HG datasets demonstrate the significant superiority of our proposed MV-HetGNN compared to the state-of-the-art baselines in various downstream tasks, e . g . node classification, node clustering, and link prediction.

18 October 2023 in The Innovation
Verified
Journal Article
Open access
YXYongjun Xu
Yongjun Xu
FWFei Wang
Fei Wang
ZAZhulin An
Zhulin An
QWQi Wang
Qi Wang
ZZZhao Zhang
Zhao Zhang