HackGAN
Harmonious Cross-Network Mapping Using CycleGAN With Wasserstein–Procrustes Learning for Unsupervised Network Alignment
Bibliographic Data
| ID | 22108226 |
|---|---|
| Authors | Linyao Yang (0000-0003-0826-9453, Chinese Academy of Sciences), Xiao Wang (0000-0001-8231-6778, Chinese Academy of Sciences), Jun Zhang (0000-0003-1706-1611, Wuhan University), Jun Jason Zhang (0000-0001-6908-2671, Wuhan University), Jun Yang (0000-0001-6740-4358, Wuhan University), Yancai Xu (Chinese Academy of Sciences), Jiachen Hou (Macau University of Science and Technology), Kejun Xin (Nanjing Joinmap Data Research Institute, Nanjing, China), Fei‐yue Wang (0000-0001-9185-3989, Chinese Academy of Sciences) |
| Year | 2023 |
| Volume | 10 |
| Issue | 2 |
| Pages | 746-759 |
| Publication date | 2023-04-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2022.3144350 |
| OpenAlex | W4225568060 |
| Language | EN |
| Citations received | 2 |
| References cited | 46 |
Network alignment (NA) that identifies equivalent nodes across networks is an effective tool for integrating knowledge from multiple networks. The state-of-the-art NA methods learn inter-network node similarities based on labeled anchor links, which are costly, time-consuming, and difficult to acquire. Therefore, a few unsupervised network alignment (UNA) methods propose solving NA problems without anchor links. However, most existing UNA methods rely on discriminative attributes to capture nodes’ similarities and are hard to obtain optimal one-to-one alignments. Toward these issues, this article proposes a novel method named HackGAN to solve the UNA problem solely based on the structural information. Specifically, HackGAN represents nodes with embeddings based on an unsupervised graph neural network (GNN) to capture their global and local structural features. After that, it initializes mapping functions to transform the embedding spaces of different networks into the same vector space by iteratively solving the Wasserstein–Procrustes problem. The mapping functions are then refined by an adversarial model with cycle-consistency and Sinkhorn distance losses to obtain optimized one-to-one mappings. Based on the distances between mapped embeddings, accurate and robust results are obtained with a collective alignment algorithm. Experimental comparisons on both synthetic and real-world datasets demonstrate the superiority of HackGAN
Algorithm · Artificial neural network · Data mining · Discriminative model · Embedding · Graph · Procrustes analysis · Unsupervised learning · Advanced Graph Neural Networks · Bioinformatics and Genomic Networks · Complex Network Analysis Techniques · Computer Science · Artificial Intelligence · Theoretical Computer Science
| Citations per year | 1 |
|---|---|
| Citation span | 2024 - 2024 (1) |
| Highly cited | No |