Xianju Zheng

Xianju Zheng


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
18 November 2025 in Journal of Seismic Exploration
Verified
Journal Article
Open access
PDF file
ZQZiyu Qin
Ziyu Qin
XZXianju Zheng
Xianju Zheng
WWWenhua Wang
Wenhua Wang
First-arrival picking of seismic data is one of the key steps in seismic data processing. When seismic data have low signal-to-noise ratio (SNR) and weak first-arrival energy, accurately and efficiently picking first arrivals remain a critical challenge for most automatic picking methods. To address this issue, this paper proposes a Multi-perspective Residual Long Short-Term Memory (M-Res-LSTM) network. This network integrates the spatial feature extraction advantage of Residual Networks and the temporal dynamic modeling capability of LSTM networks, while introducing a coordinate attention mechanism. Through multi-perspective learning in both time and frequency domains, it effectively improves the reliability of automatic first-arrival picking. First, this paper elaborates on the core principle of the M-Res-LSTM network for automatic first-arrival picking: the amplitude, frequency, and phase features of seismic data are used as network inputs, and the accurately picked first arrivals manually serve as network outputs. After training the network using a supervised learning approach, the well-trained model is applied to perform automatic first-arrival picking. Second, an analysis of the network’s hyperparameters is conducted to determine the optimal parameter configuration. Finally, automatic first-arrival picking tests are carried out on seismic datasets with different characteristics, and the picking results are compared with those obtained by the energy ratio method, single-input Res-LSTM, and Swin-Transformer. The results demonstrate that the proposed M-Res-LSTM method maintains good stability and accuracy even in complex scenarios with low first-arrival energy and poor SNR.

7 July 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
ZZZhengjuan Zhou
Zhengjuan Zhou
XZXianju Zheng
Xianju Zheng
YYYue Yu
Yue Yu
XDXin Dong
Xin Dong
SLShaolong Li
Shaolong Li
In the domain of multi-label classification, label correlations play a crucial role in enhancing prediction precision. However, traditional methods heavily depend on ground-truth label sets, which can be incompletely tagged due to the diverse backgrounds of annotators and the significant cost associated with procuring extensive labeled datasets. To address these challenges, this paper introduces a novel multi-label classification method called updating Correlation-enhanced Feature Learning (uCeFL), which extracts label correlations directly from the data instances, circumventing the dependency on potentially incomplete label sets. uCeFL initially computes a revised label matrix by multiplying the incomplete label matrix with the label correlations extracted from the data matrix. This revised matrix is then utilized to enrich the original data features, enabling a neural network to learn correlation-enhanced representations that capture intricate relationships between data features, labels, and their interactions. Notably, label correlations are not static; they are dynamically updated during the neural network’s training process. Extensive experiments carried out on various datasets emphasize the effectiveness of the proposed approach. By leveraging label correlations within data instances, along with the hierarchical learning capabilities of neural networks, it offers a significant improvement in multi-label classification, even in scenarios with incomplete labels.

Verified
Journal Article
Open access
PDF file
WZWei Zhang
Wei Zhang
YSYimin Shen
Yimin Shen
HZHang Zhou
Hang Zhou
BZBo Zhou
Bo Zhou
XZXianju Zheng
Xianju Zheng
Xiang ChenXiang Chen
Xiang Chen
Systemic risk propagation in modern financial markets is characterized by non-linear contagion and rapid topological evolution, rendering traditional static monitoring methods ineffective. Existing Graph Neural Networks (GNNs) often struggle to capture “structural breaks” during crises due to their reliance on static adjacency assumptions and isotropic aggregation. To address these challenges, this study proposes the Temporal Attentive Graph Networks (TAGN), a dynamic framework designed for extreme volatility prediction and financial surveillance. TAGN constructs an incremental multi-scale graph by fusing high-frequency trading data, supply chain linkages, and institutional co-holdings to model heterogeneous risk transmission channels. Technically, it employs a deeply coupled GAT-GRU architecture, where the Graph Attention Network (GAT) dynamically assigns weights to contagion sources, and the Gated Recurrent Unit (GRU) memorizes the trajectory of structural evolution. Extensive experiments on the S&P 500 dataset (2018–2024) demonstrate that TAGN significantly outperforms state-of-the-art baselines, including WinGNN and PatchTST, achieving an AUC of 0.890 and a Precision at 50 of 61.5%. Notably, a risk early-warning index derived from TAGN exhibits a 1–2 week lead time over the VIX index during major market stress events, such as the Silicon Valley Bank collapse. This research facilitates a paradigm shift from historical statistical estimation to dynamic network-aware sensing, offering interpretable tools for RegTech applications.

11 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
WZWei Zhang
Wei Zhang
YSYimin Shen
Yimin Shen
HZHang Zhou
Hang Zhou
BZBo Zhou
Bo Zhou
XZXianju Zheng
Xianju Zheng
Xiang ChenXiang Chen
Xiang Chen
Addressing the limitations of conventional financial time series models in capturing modern market dynamics, this study introduces a novel financial monitoring framework based on Temporal Attentive Graph Networks (TAGN). The TAGN model integrates Graph Attention Networks (GAT) and Gated Recurrent Units (GRU) to simultaneously capture spatial dependencies among financial entities and the dynamic evolution of network structure. The framework uses a multi-relational dynamic graph of 50 NASDAQ stocks. Node features fuse multi-scale information (micro, meso, macro), and the graph structure integrates price correlation, supply chain, and institutional co-holdings. Compared to benchmarks (Logistic Regression, GCN, GCN-LSTM), TAGN demonstrates superior performance (AUC: 0.89) in predicting stocks likely to experience extreme volatility (>±15%) within three months. Empirical analysis (2018–2023) effectively quantifies network imprints of major events (e.g., 45% average edge weight surge during COVID-19; community stability Jaccard similarity drop to 0.34 following the SVB incident). An ablation study confirms the critical contribution of the attention and temporal components. Finally, by generating a risk early-warning index integrating network topology and model output, this research offers a new tool for systemic risk quantification and proactive anticipation.