A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature
This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/3/369 |
| _version_ | 1797318484940554240 |
|---|---|
| author | Chunjiang Liu Yikun Han Haiyun Xu Shihan Yang Kaidi Wang Yongye Su |
| author_facet | Chunjiang Liu Yikun Han Haiyun Xu Shihan Yang Kaidi Wang Yongye Su |
| author_sort | Chunjiang Liu |
| collection | DOAJ |
| description | This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced the performance across all models tested. For example, integrating the Louvain model with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains were noted when the Louvain model was paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent increase in performance—reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations—highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques. |
| first_indexed | 2024-03-08T03:53:05Z |
| format | Article |
| id | doaj.art-cf27a28674254f07ad17e5be83679f47 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-08T03:53:05Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-cf27a28674254f07ad17e5be83679f472024-02-09T15:18:06ZengMDPI AGMathematics2227-73902024-01-0112336910.3390/math12030369A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific LiteratureChunjiang Liu0Yikun Han1Haiyun Xu2Shihan Yang3Kaidi Wang4Yongye Su5Chengdu Library and Information Center, Chinese Academy of Sciences, Chengdu 610299, ChinaDepartment of Statistics, University of Michigan, Ann Arbor, MI 48109, USASchool of Business, Shandong University of Technology, Zibo 255000, ChinaFaculty of Management and Economics, Kunming University of Science and Technology, Kunming 650031, ChinaSchool of Business, Macau University of Science and Technology, Macau 999078, ChinaDepartment of Computer Science, Purdue University, West Lafayette, IN 47907, USAThis study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced the performance across all models tested. For example, integrating the Louvain model with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains were noted when the Louvain model was paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent increase in performance—reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations—highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques.https://www.mdpi.com/2227-7390/12/3/369link predictiongraph neural networkcommunity detectionnetwork analysiscitation graphdeep learning |
| spellingShingle | Chunjiang Liu Yikun Han Haiyun Xu Shihan Yang Kaidi Wang Yongye Su A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature Mathematics link prediction graph neural network community detection network analysis citation graph deep learning |
| title | A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature |
| title_full | A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature |
| title_fullStr | A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature |
| title_full_unstemmed | A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature |
| title_short | A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature |
| title_sort | community detection and graph neural network based link prediction approach for scientific literature |
| topic | link prediction graph neural network community detection network analysis citation graph deep learning |
| url | https://www.mdpi.com/2227-7390/12/3/369 |
| work_keys_str_mv | AT chunjiangliu acommunitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT yikunhan acommunitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT haiyunxu acommunitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT shihanyang acommunitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT kaidiwang acommunitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT yongyesu acommunitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT chunjiangliu communitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT yikunhan communitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT haiyunxu communitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT shihanyang communitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT kaidiwang communitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature AT yongyesu communitydetectionandgraphneuralnetworkbasedlinkpredictionapproachforscientificliterature |