Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph
Network alignment, a foundational technique for cross-domain applications such as recommendation systems and knowledge fusion, faces significant challenges in balancing computational efficiency and alignment accuracy. Although graph neural networks (GNNs) effectively capture structural and semantic...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10918943/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849392080080601088 |
|---|---|
| author | Lei Zhang Feng Qian |
| author_facet | Lei Zhang Feng Qian |
| author_sort | Lei Zhang |
| collection | DOAJ |
| description | Network alignment, a foundational technique for cross-domain applications such as recommendation systems and knowledge fusion, faces significant challenges in balancing computational efficiency and alignment accuracy. Although graph neural networks (GNNs) effectively capture structural and semantic relationships, their computational intensity—stemming from multi-layer matrix operations and high memory consumption—severely limits scalability. To address these limitations, this paper proposes ENAMOR (Efficient Network AlignMent via Quotient gRaph), an unsupervised framework incorporating three key components: 1) multi-scale representation learning that hierarchically aggregates local and global structural patterns through GNN layers; 2) embedding-driven graph coarsening via hashing-based quotient graph construction, reducing computational complexity by 60–80% while preserving topological and attribute information; and 3) Matched Neighborhood Consistency (MNC) optimization, which iteratively refines alignment matrices by enforcing structural congruence constraints. Extensive experiments on three real-world datasets (Douban Online-Offline, Allmovie-Imdb, ACM-DBLP) demonstrate that ENAMOR achieves a 13.47–94.56% reduction in runtime compared to state-of-the-art methods, alongside improvements of 0.27–13.47 percentage points in mean average precision (MAP) and 0.15–8.17 percentage points in precision@5. The framework effectively balances efficiency and accuracy, providing a scalable solution for cross-network analysis tasks. |
| format | Article |
| id | doaj-art-c67c738b80bd4b9187ce32f8a9c55ee6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c67c738b80bd4b9187ce32f8a9c55ee62025-08-20T03:40:51ZengIEEEIEEE Access2169-35362025-01-0113464954651310.1109/ACCESS.2025.354978710918943Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient GraphLei Zhang0Feng Qian1https://orcid.org/0009-0007-7879-0515School of Mathematics and Computer Science, Tongling University, Tongling, ChinaSchool of Mathematics and Computer Science, Tongling University, Tongling, ChinaNetwork alignment, a foundational technique for cross-domain applications such as recommendation systems and knowledge fusion, faces significant challenges in balancing computational efficiency and alignment accuracy. Although graph neural networks (GNNs) effectively capture structural and semantic relationships, their computational intensity—stemming from multi-layer matrix operations and high memory consumption—severely limits scalability. To address these limitations, this paper proposes ENAMOR (Efficient Network AlignMent via Quotient gRaph), an unsupervised framework incorporating three key components: 1) multi-scale representation learning that hierarchically aggregates local and global structural patterns through GNN layers; 2) embedding-driven graph coarsening via hashing-based quotient graph construction, reducing computational complexity by 60–80% while preserving topological and attribute information; and 3) Matched Neighborhood Consistency (MNC) optimization, which iteratively refines alignment matrices by enforcing structural congruence constraints. Extensive experiments on three real-world datasets (Douban Online-Offline, Allmovie-Imdb, ACM-DBLP) demonstrate that ENAMOR achieves a 13.47–94.56% reduction in runtime compared to state-of-the-art methods, alongside improvements of 0.27–13.47 percentage points in mean average precision (MAP) and 0.15–8.17 percentage points in precision@5. The framework effectively balances efficiency and accuracy, providing a scalable solution for cross-network analysis tasks.https://ieeexplore.ieee.org/document/10918943/Network alignmentgraph neural networksgraph coarseningquotient graphmatched neighborhood consistency |
| spellingShingle | Lei Zhang Feng Qian Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph IEEE Access Network alignment graph neural networks graph coarsening quotient graph matched neighborhood consistency |
| title | Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph |
| title_full | Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph |
| title_fullStr | Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph |
| title_full_unstemmed | Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph |
| title_short | Enhancing the Efficiency of Unsupervised Network Alignment Using Quotient Graph |
| title_sort | enhancing the efficiency of unsupervised network alignment using quotient graph |
| topic | Network alignment graph neural networks graph coarsening quotient graph matched neighborhood consistency |
| url | https://ieeexplore.ieee.org/document/10918943/ |
| work_keys_str_mv | AT leizhang enhancingtheefficiencyofunsupervisednetworkalignmentusingquotientgraph AT fengqian enhancingtheefficiencyofunsupervisednetworkalignmentusingquotientgraph |