MHHCR: Multi-behavior Heterogeneous Hypergraph Contrastive Recommendation DOI
Yongtai Li, Weihai Lu

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 91 - 102

Опубликована: Ноя. 30, 2024

Язык: Английский

Enhancing neighborhood-based co-clustering contrastive learning for multi-entity recommendation DOI
Juan Liao,

Aman Jantan,

Zhe Liu

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 148, С. 110425 - 110425

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Decision Preference Networks in Ensemble Classification learning: Focusing on decision preferences and influences DOI

X. Li,

Min Guo, Kaiguang Wang

и другие.

Information Processing & Management, Год журнала: 2025, Номер 62(4), С. 104133 - 104133

Опубликована: Март 23, 2025

Язык: Английский

Процитировано

0
Information Compensation Graph Contrastive Learning for Recommendation DOI Creative Commons
Zhenhai Wang,

Yunlong Guo,

Xiaoli Zhao

и другие.

Neural Processing Letters, Год журнала: 2025, Номер 57(3)

Опубликована: Май 10, 2025

Язык: Английский

Процитировано

0
A Student Performance Prediction Model Based on Hierarchical Belief Rule Base with Interpretability DOI Creative Commons

Minjie Liang,

Guohui Zhou, Wei He

и другие.

Mathematics, Год журнала: 2024, Номер 12(14), С. 2296 - 2296

Опубликована: Июль 22, 2024

Predicting student performance in the future is a crucial behavior prediction problem education. By predicting performance, educational experts can provide individualized instruction, optimize allocation of resources, and develop strategies. If results are unreliable, it difficult to earn trust experts. Therefore, methods need satisfy requirement interpretability. For this reason, model constructed paper using belief rule base (BRB). BRB not only combines expert knowledge, but also has good There two problems applying prediction: first, modeling process, system too complex due large number indicators involved. Secondly, interpretability be compromised during optimization process. To overcome these challenges, introduces hierarchical with (HBRB-I) for prediction. First, analyzes how HBRB-I achieves Then, an attribute grouping method proposed construct structure by reasonably organizing indicators, so as effectively reduce complexity model. Finally, objective function considering designed projected covariance matrix adaptive evolution strategy (P-CMA-ES) algorithm improved. The aim ensure that remains interpretable after optimization. conducting experiments on dataset, demonstrated performs well terms both accuracy

Язык: Английский

Процитировано

2
Financial risk assessment of imbalanced data based on nonlinear causal time-series network DOI
Xiaoyang Li, Weimin Li,

Xiao Yu

и другие.

Information Processing & Management, Год журнала: 2024, Номер 62(3), С. 104025 - 104025

Опубликована: Дек. 24, 2024

Язык: Английский

Процитировано

1
Group Behavior Prediction and Evolution in Social Networks DOI
Jingchao Wang, Xinyi Zhang, Weimin Li

и другие.

IEEE Intelligent Systems, Год журнала: 2024, Номер 39(2), С. 62 - 65

Опубликована: Март 1, 2024

Group behavior prediction and evolution in social networks aims to accurately predict model trends patterns of group through detailed analysis massive user data, which is great significance the formulation marketing strategies, experience, business strategies. Therefore, experts various fields are actively exploring potential network data develop more accurate models. This article provides an overview these studies explores challenges opportunities faced by networks.

Язык: Английский

Процитировано

0
MHHCR: Multi-behavior Heterogeneous Hypergraph Contrastive Recommendation DOI
Yongtai Li, Weihai Lu

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 91 - 102

Опубликована: Ноя. 30, 2024

Язык: Английский

Процитировано

0