Guojia Wan

Dr. Guojia Wan

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
25 July 2023 in Knowledge-Based Systems
Verified
Journal Article
Closed access
DZDong Zhao
Dong Zhao
GWGuojia Wan
Guojia Wan
YZYibing Zhan
Yibing Zhan
ZWZengmao Wang
Zengmao Wang
LDLiang Ding
Liang Ding
BDBo Du
Bo Du

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
TXTianle Xia
Tianle Xia
LDLiang Ding
Liang Ding
GWGuojia Wan
Guojia Wan
YZYibing Zhan
Yibing Zhan
BDBo Du
Bo Du
DTDacheng Tao
Dacheng Tao
Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements~(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.

8 June 2023 in Future Generation Computer Systems
Verified
Journal Article
Closed access
GWGuojia Wan
Guojia Wan
ZZZhengyun Zhou
Zhengyun Zhou
ZZZhigao Zheng
Zhigao Zheng
BDBo Du
Bo Du

24 January 2025 in Data Science and Engineering
Verified
Journal Article
Open access
PDF file
ZZZhengyun Zhou
Zhengyun Zhou
GWGuojia Wan
Guojia Wan
BDBo Du
Bo Du
Link prediction is essential for identifying hidden relationships within network data, with significant implications for fields such as social network analysis and bioinformatics. Traditional methods often overlook potential relationships among common neighbors, limiting their effectiveness in utilizing graph information fully. To address this, we introduce a novel approach, Common Neighbor Completion with Information Entropy (IECNC), which enhances model expressiveness by considering logical neighbor relationships. Our method integrates a dynamic node function with a Message Passing Neural Network (MPNN), focusing on first-order neighbors and employing set-based aggregation to improve missing link predictions. By combining the information entropy of probabilistic predictions of common neighbors with MPNN and leveraging information entropy to assess uncertainty in adjacent connections, our approach significantly enhances prediction accuracy. Experimental results demonstrate that our IECNC method achieves optimal performance across multiple datasets, surpassing existing techniques. Furthermore, visualizations confirm that our model effectively captures and accurately learns feature information from various categories, Demonstrating the method’s efficacy and adaptability.

11 April 2024 in World Wide Web
Verified
Journal Article
Closed access
PDF file
ZZZhengyun Zhou
Zhengyun Zhou
GWGuojia Wan
Guojia Wan
SPShirui Pan
Shirui Pan
Jia WUJia WU
Jia WU
WHWenbin Hu
Wenbin Hu
BDBo Du
Bo Du

25 May 2025 in Neural Networks
Verified
Journal Article
Closed access
MLMinghui Liao
Minghui Liao
GWGuojia Wan
Guojia Wan
WHWenbin Hu
Wenbin Hu
BDBo Du
Bo Du