Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery
In the context of organizers’ behavior scheduling optimization, accurately assessing and optimizing scheduling programs is essential. This paper introduces HyperFusion, a framework designed to enhance scheduling efficiency through hypergraph learning techniques and an adaptive feature fus...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838518/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592839514521600 |
|---|---|
| author | Ziqi Xu Huiqi Zhang |
| author_facet | Ziqi Xu Huiqi Zhang |
| author_sort | Ziqi Xu |
| collection | DOAJ |
| description | In the context of organizers’ behavior scheduling optimization, accurately assessing and optimizing scheduling programs is essential. This paper introduces HyperFusion, a framework designed to enhance scheduling efficiency through hypergraph learning techniques and an adaptive feature fusion model tailored to organizers’ behavioral patterns. The model categorizes and evaluates scheduling methods by identifying peer groups of organizers who share similar behavioral and operational attributes. Addressing challenges such as variability in scheduling approaches across different environments and the availability of diverse behavioral data, HyperFusion utilizes hypergraph-based feature fusion to identify high-quality scheduling and behavioral features that reflect each organizer’s unique scheduling style and operational impact. Employing a probabilistic model, the framework represents each organizer’s attributes in a latent space, enabling a nuanced understanding of their contributions. A large-scale hypergraph is constructed to map relationships and similarities among organizers, identifying dense subgraphs or “circles” of organizers with shared attributes. By mining these high-order relationships within these “organizer circles”, HyperFusion enhances scheduling quality and provides adaptive fusion of behavioral features, optimizing the scheduling process to meet the objectives of high-order relationship discovery. Experiments conducted on a dataset of organizers from 36 prominent institutions (our complied data set) demonstrate the model’s effectiveness in improving scheduling programs, underscoring its capability to align scheduling practices with adaptive, data-driven optimization and fostering a responsive and efficient scheduling system. |
| format | Article |
| id | doaj-art-1f4418997f024a05ac83ce82b60a255e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1f4418997f024a05ac83ce82b60a255e2025-01-21T00:02:20ZengIEEEIEEE Access2169-35362025-01-0113102771028810.1109/ACCESS.2025.352865110838518Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships DiscoveryZiqi Xu0Huiqi Zhang1https://orcid.org/0009-0002-9157-7691School of Business, Macau University of Science and Technology, Macau, ChinaSchool of Economics and Management, Beijing Jiaotong University, Beijing, ChinaIn the context of organizers’ behavior scheduling optimization, accurately assessing and optimizing scheduling programs is essential. This paper introduces HyperFusion, a framework designed to enhance scheduling efficiency through hypergraph learning techniques and an adaptive feature fusion model tailored to organizers’ behavioral patterns. The model categorizes and evaluates scheduling methods by identifying peer groups of organizers who share similar behavioral and operational attributes. Addressing challenges such as variability in scheduling approaches across different environments and the availability of diverse behavioral data, HyperFusion utilizes hypergraph-based feature fusion to identify high-quality scheduling and behavioral features that reflect each organizer’s unique scheduling style and operational impact. Employing a probabilistic model, the framework represents each organizer’s attributes in a latent space, enabling a nuanced understanding of their contributions. A large-scale hypergraph is constructed to map relationships and similarities among organizers, identifying dense subgraphs or “circles” of organizers with shared attributes. By mining these high-order relationships within these “organizer circles”, HyperFusion enhances scheduling quality and provides adaptive fusion of behavioral features, optimizing the scheduling process to meet the objectives of high-order relationship discovery. Experiments conducted on a dataset of organizers from 36 prominent institutions (our complied data set) demonstrate the model’s effectiveness in improving scheduling programs, underscoring its capability to align scheduling practices with adaptive, data-driven optimization and fostering a responsive and efficient scheduling system.https://ieeexplore.ieee.org/document/10838518/Hyperfusionhypergraph learningorganizershigh-orderdense subgraphs |
| spellingShingle | Ziqi Xu Huiqi Zhang Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery IEEE Access Hyperfusion hypergraph learning organizers high-order dense subgraphs |
| title | Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery |
| title_full | Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery |
| title_fullStr | Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery |
| title_full_unstemmed | Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery |
| title_short | Hypergraph-Based Organizers’ Behavior Scheduling Optimization: High-Order Relationships Discovery |
| title_sort | hypergraph based organizers x2019 behavior scheduling optimization high order relationships discovery |
| topic | Hyperfusion hypergraph learning organizers high-order dense subgraphs |
| url | https://ieeexplore.ieee.org/document/10838518/ |
| work_keys_str_mv | AT ziqixu hypergraphbasedorganizersx2019behaviorschedulingoptimizationhighorderrelationshipsdiscovery AT huiqizhang hypergraphbasedorganizersx2019behaviorschedulingoptimizationhighorderrelationshipsdiscovery |