Zhejian Yang

Zhejian Yang

Auto-generated profile, based on publicly available information

Zhejian Yang

School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, Jilin University, Changchun, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 May 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
KYKang Yang
Kang Yang
ZYZhiwei Yang
Zhiwei Yang
SZSongwei Zhao
Songwei Zhao
ZYZhejian Yang
Zhejian Yang
SZSinuo Zhang
Sinuo Zhang
HCHechang Chen
Hechang Chen

3 November 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YLYang Li
Yang Li
BYBo Yang
Bo Yang
XZXuehua Zhao
Xuehua Zhao
ZYZhejian Yang
Zhejian Yang
HCHechang Chen
Hechang Chen

4 October 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
TLTianyi Liu
Tianyi Liu
HCHechang Chen
Hechang Chen
JHJifeng Hu
Jifeng Hu
ZYZhejian Yang
Zhejian Yang
BYBo Yu
Bo Yu
YCYi Chang
Yi Chang

16 September 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JHJifeng Hu
Jifeng Hu
LSLi Shen
Li Shen
SHSili Huang
Sili Huang
ZYZhejian Yang
Zhejian Yang
HCHechang Chen
Hechang Chen
DTDacheng Tao
Dacheng Tao
Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks’ datasets are usually static. However, in real-world applications, such as robotic control of reinforcement learning (RL), the tasks are changing, and new tasks arise in a sequential order. This situation poses the new challenge of plasticity–stability tradeoff for training an agent who can adapt to task changes and retain acquired knowledge. In view of this, we propose a rehearsal-based continual diffusion model, called continual diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability). Specifically, we first construct an offline benchmark that contains 90 tasks from multiple domains. Then, we train the CoD on each task with sequential modeling and conditional generation for making decisions. Next, we preserve a small portion of previous datasets as the rehearsal buffer and replay it to retain the acquired knowledge. Extensive experiments on a series of tasks show that CoD can achieve a promising plasticity–stability tradeoff and outperform existing diffusion-based methods and other representative baselines on most tasks. The source code is available at https://github.com/JF-Hu/Continual_Diffuser.

23 July 2025 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
SZSongwei Zhao
Songwei Zhao
BYBo Yu
Bo Yu
SZSinuo Zhang
Sinuo Zhang
ZYZhejian Yang
Zhejian Yang
JHJifeng Hu
Jifeng Hu
HCHechang Chen
Hechang Chen
Graph neural networks (GNNs) have garnered significant attention for their competitive performance on graph-structured data. However, many existing methods are commonly constrained by the homophily assumption, making them overly reliant on the uniform neighbor propagation, which limits their ability to generalize to heterophilous graphs. Although some approaches extend aggregation to multi-hop neighbors, adapting neighborhood sizes on a per-node basis remains a significant challenge. In view of this, we propose an Evolutionary Graph Neural Network (EGNN) with adaptive structure-level aggregation and label smoothing, offering a novel solution to the aforementioned drawback. The core innovation of EGNN lies in assigning each node a personalized neighborhood structure utilizing behavior-level crossover and mutation. Specifically, we first adaptively search for the optimal structure-level neighborhoods for nodes within the solution space, leveraging the exploratory capabilities of evolutionary computation. This approach enhances the exchange of information between the target node and surrounding nodes, achieving a smooth vector representation. Subsequently, we adopt the optimal structure obtained through evolutionary search to perform label smoothing, further boosting the robustness of the framework. We conduct experiments on nine real-world networks with different homophily ratios, where outstanding performance demonstrates that the ability of EGNN can match or surpass SOTA baselines.

15 August 2025 in Pattern Recognition
Verified
Journal Article
Closed access
ZYZhejian Yang
Zhejian Yang
YLYang Li
Yang Li
BYBo Yu
Bo Yu
JHJifeng Hu
Jifeng Hu
HCHechang Chen
Hechang Chen