Lizhen Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lizhen Wang has a total of 135 co-authors. Here are the top co-authors by number of shared publications:
- Hongmei Chen
School of Information Science and Engineering, Yunnan University, Kunming, China
29 shared publications - Peizhong Yang
Yunnan University
28 shared publications - Lihua Zhou
Yunnan University
24 shared publications - Vanha Tran
FPT University
13 shared publications Lihua Zhou
11 shared publicationsPeizhong Yang
Yunnan University
11 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (12) , 7943-7958
An Efficient Method for Mining Spatial Co-Location Patterns Under Size Constraints
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (12) , 7943-7958
An Efficient Method for Mining Spatial Co-Location Patterns Under Size Constraints
- Open Access
- 28 September 2026
- Published by Elsevier in SSRN Electronic Journal
FairMoE:A Functionally Specialized Mixture-of-Experts Framework for Fair Graph Node Classification
Fair graph node classification aims to reduce the dependence of predictions on sensitive attributes while preserving predictive utility. However, many existing methods rely on a shared representation path for fairness and utility, which may couple potentially competing objectives. In addition, fairness-oriented modeling is often centered on local neighborhoods, which may overlook fairness-related information from broader structural contexts. To address these issues, we propose FairMoE, a mixture-of-experts framework for fair graph node classification. FairMoE functionally separates the two objectives through a Fairness Expert Group and a Utility Expert Group, which respectively perform fairness-oriented and utility-oriented learning. Within the Fairness Expert Group, multiple Fairness Experts operate over different receptive fields to learn fairness-oriented representations from local and higher-order structural contexts. In parallel, the Utility Expert Group employs complementary experts to preserve task-discriminative information. The two outputs are then coordinated by a Dynamic Gate, which produces node-specific weights to control how much utility information supplements the fairness-oriented prediction. Experiments on multiple real-world datasets demonstrate that FairMoE achieves a competitive trade-off between fairness and classification utility, with particularly strong results on fairness metrics. Further ablation and structural analyses support the effectiveness of the core designs. The code will be made publicly available upon acceptance.
- 28 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFairMoE:A Functionally Specialized Mixture-of-Experts Framework for Fair Graph Node Classification
Fair graph node classification aims to reduce the dependence of predictions on sensitive attributes while preserving predictive utility. However, many existing methods rely on a shared representation path for fairness and utility, which may couple potentially competing objectives. In addition, fairness-oriented modeling is often centered on local neighborhoods, which may overlook fairness-related information from broader structural contexts. To address these issues, we propose FairMoE, a mixture-of-experts framework for fair graph node classification. FairMoE functionally separates the two objectives through a Fairness Expert Group and a Utility Expert Group, which respectively perform fairness-oriented and utility-oriented learning. Within the Fairness Expert Group, multiple Fairness Experts operate over different receptive fields to learn fairness-oriented representations from local and higher-order structural contexts. In parallel, the Utility Expert Group employs complementary experts to preserve task-discriminative information. The two outputs are then coordinated by a Dynamic Gate, which produces node-specific weights to control how much utility information supplements the fairness-oriented prediction. Experiments on multiple real-world datasets demonstrate that FairMoE achieves a competitive trade-off between fairness and classification utility, with particularly strong results on fairness metrics. Further ablation and structural analyses support the effectiveness of the core designs. The code will be made publicly available upon acceptance.
- 18 September 2026
- Published by Elsevier in Information Fusion
- Vol. 139
MCA-SSL: A synergistic fusion-optimization-alignment loop for incomplete multi-view clustering
- 18 September 2026
- Published by Elsevier in Information Fusion
- Vol. 139
MCA-SSL: A synergistic fusion-optimization-alignment loop for incomplete multi-view clustering
- Open Access
- 25 July 2026
- Published by Springer Nature in Data Science and Engineering
- p. 1-23
Mining Sustained Emerging Spatio-Temporal Co-occurrence Patterns from Dynamic Spatial Databases
- 25 July 2026
- Published by Springer Nature in Data Science and Engineering
- p. 1-23
Open AccessMining Sustained Emerging Spatio-Temporal Co-occurrence Patterns from Dynamic Spatial Databases
- 24 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Learning inductive representations from LBSNs for next POI recommendation
- 24 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Learning inductive representations from LBSNs for next POI recommendation
- 21 July 2026
- Published by Springer Nature
- p. 249-262
Direction and Time-Aware Location Selection for Mobile Users
- 21 July 2026
- Published by Springer Nature
- p. 249-262
Direction and Time-Aware Location Selection for Mobile Users
- 12 July 2026
- Published by Springer Nature
- p. 331-344
Spatio-Temporal Semantic-Enhanced Contrastive Learning for Friend Recommendation
- 12 July 2026
- Published by Springer Nature
- p. 331-344
Spatio-Temporal Semantic-Enhanced Contrastive Learning for Friend Recommendation
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4511-4527
Maximal Prevalent Region Identification and Classification for Spatial Co-location Patterns
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4511-4527
Maximal Prevalent Region Identification and Classification for Spatial Co-location Patterns
- Open Access
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 18-23
A Decoder-Enhanced Autoencoder for Heterogeneous Graph Representation Learning
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 18-23
Open AccessA Decoder-Enhanced Autoencoder for Heterogeneous Graph Representation Learning
- 18 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
Mining co-location evolving sequences from spatio-temporal data
- 18 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
Mining co-location evolving sequences from spatio-temporal data