Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918155711938560 |
|---|---|
| author | Huang, Dong Song, Xianwen Yang, Pengkun |
| author_facet | Huang, Dong Song, Xianwen Yang, Pengkun |
| contents | This paper studies the problem of recovering the hidden vertex correspondence between two correlated random graphs. We propose the partially correlated Erdős-Rényi graphs model, wherein a pair of induced subgraphs with a certain number are correlated. We investigate the information-theoretic thresholds for recovering the latent correlated subgraphs and the hidden vertex correspondence. We prove that there exists an optimal rate for partial recovery for the number of correlated nodes, above which one can correctly match a fraction of vertices and below which correctly matching any positive fraction is impossible, and we also derive an optimal rate for exact recovery. In the proof of possibility results, we propose correlated functional digraphs, which partition the edges of the intersection graph into two types of components, and bound the error probability by lower-order cumulant generating functions. The proof of impossibility results build upon the generalized Fano's inequality and the recovery thresholds settled in correlated Erdős-Rényi graphs model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05428 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs Huang, Dong Song, Xianwen Yang, Pengkun Information Theory Statistics Theory Machine Learning This paper studies the problem of recovering the hidden vertex correspondence between two correlated random graphs. We propose the partially correlated Erdős-Rényi graphs model, wherein a pair of induced subgraphs with a certain number are correlated. We investigate the information-theoretic thresholds for recovering the latent correlated subgraphs and the hidden vertex correspondence. We prove that there exists an optimal rate for partial recovery for the number of correlated nodes, above which one can correctly match a fraction of vertices and below which correctly matching any positive fraction is impossible, and we also derive an optimal rate for exact recovery. In the proof of possibility results, we propose correlated functional digraphs, which partition the edges of the intersection graph into two types of components, and bound the error probability by lower-order cumulant generating functions. The proof of impossibility results build upon the generalized Fano's inequality and the recovery thresholds settled in correlated Erdős-Rényi graphs model. |
| title | Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs |
| topic | Information Theory Statistics Theory Machine Learning |
| url | https://arxiv.org/abs/2406.05428 |