Yu Liu

Mr. Yu Liu

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
5 May 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
JYJiawei Ye
Jiawei Ye
YCYanting Chen
Yanting Chen
ASAierpanjiang Simayi
Aierpanjiang Simayi
YLYu Liu
Yu Liu
Zhihu LuZhihu Lu
Zhihu Lu
JWJie Wu
Jie Wu
This paper presents TCReC, an innovative model designed for reconstructing network traffic characteristics in the presence of packet loss. With the rapid expansion of wireless networks driven by edge computing, IoT, and 5G technologies, challenges such as transmission instability, channel competition, and environmental interference have led to significant packet loss rates, adversely impacting deep learning-based network traffic analysis tasks. To address this issue, TCReC leverages masked autoencoder techniques to reconstruct missing traffic features, ensuring reliable input for downstream tasks in edge computing scenarios. Experimental results demonstrate that TCReC maintains detection model accuracy within 10% of the original data, even under packet loss rates as high as 70%. For instance, on the ISCX-VPN-2016 dataset, TCReC achieves a Reconstruction Ability Index (RAI) of 94.02%, while on the CIC-IDS-2017 dataset, it achieves an RAI of 94.99% when combined with LSTM, significantly outperforming other methods such as Transformer, KNN, and RNN. Additionally, TCReC exhibits robustness across various packet loss scenarios, consistently delivering high-quality feature reconstruction for both attack traffic and common Internet application data. TCReC provides a robust solution for network traffic analysis in high-loss edge computing scenarios, offering practical value for real-world deployment.

8 May 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
SLSicheng Liang
Sicheng Liang
YWYihao Wen
Yihao Wen
CHChunpu Huang
Chunpu Huang
YLYu Liu
Yu Liu
YNYichen Nie
Yichen Nie
JWJie Wu
Jie Wu
Multimodal Attributed Graphs (MAGs), which include textual, visual, and structural information, are prevalent in domains such as e-commerce and social media. However, zero-shot reasoning on MAGs remains challenging. Existing graph neural networks often produce biased representations due to modality imbalance and limited semantic reasoning, and their reliance on labeled data makes them almost incapable of handling such scenarios. Meanwhile, large language models (LLMs) exhibit strong cross-modal reasoning ability but lack explicit modeling of graph structure. To address these challenges, we propose CoMAG, a collaborative framework that unifies graph-enhanced multimodal representation learning with LLM-based reasoning. CoMAG extracts modality-specific embeddings via frozen encoders and refines them through self-supervised graph learning. It further derives discrete structural priors as symbolic tokens and aligns graph embeddings with the LLM token space, enabling prompt-based inference. Moreover, a structure-aware reasoning layer introduces gated structural cues, adaptive modality fusion, and neighborhood-consistent prediction to enhance robustness. Extensive experiments on multiple real-world MAG datasets for zero-shot tasks demonstrate the effectiveness of CoMAG, yielding consistent and notable improvements over state-of-the-art baselines. These results highlight CoMAG’s capability to tackle the fundamental challenges of zero-shot multimodal graph reasoning.

18 August 2026 in Knowledge-Based Systems
Verified
Journal Article
Closed access
SLSicheng Liang
Sicheng Liang
YWYihao Wen
Yihao Wen
CHChunpu Huang
Chunpu Huang
YLYu Liu
Yu Liu
YNYichen Nie
Yichen Nie
JWJie Wu
Jie Wu