LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909899526504448 |
|---|---|
| author | Puppala, Sai Hossain, Ismail Alam, Md Jahangir Ahad, Tanzim Talukder, Sajedul |
| author_facet | Puppala, Sai Hossain, Ismail Alam, Md Jahangir Ahad, Tanzim Talukder, Sajedul |
| contents | We propose a method that uses large language models to assist graph machine learning under personalization and privacy constraints. The approach combines data augmentation for sparse graphs, prompt and instruction tuning to adapt foundation models to graph tasks, and in-context learning to supply few-shot graph reasoning signals. These signals parameterize a Dynamic UMAP manifold of client-specific graph embeddings inside a Bayesian variational objective for personalized federated learning. The method supports node classification and link prediction in low-resource settings and aligns language model latent representations with graph structure via a cross-modal regularizer. We outline a convergence argument for the variational aggregation procedure, describe a differential privacy threat model based on a moments accountant, and present applications to knowledge graph completion, recommendation-style link prediction, and citation and product graphs. We also discuss evaluation considerations for benchmarking LLM-assisted graph machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09438 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning Puppala, Sai Hossain, Ismail Alam, Md Jahangir Ahad, Tanzim Talukder, Sajedul Machine Learning Artificial Intelligence We propose a method that uses large language models to assist graph machine learning under personalization and privacy constraints. The approach combines data augmentation for sparse graphs, prompt and instruction tuning to adapt foundation models to graph tasks, and in-context learning to supply few-shot graph reasoning signals. These signals parameterize a Dynamic UMAP manifold of client-specific graph embeddings inside a Bayesian variational objective for personalized federated learning. The method supports node classification and link prediction in low-resource settings and aligns language model latent representations with graph structure via a cross-modal regularizer. We outline a convergence argument for the variational aggregation procedure, describe a differential privacy threat model based on a moments accountant, and present applications to knowledge graph completion, recommendation-style link prediction, and citation and product graphs. We also discuss evaluation considerations for benchmarking LLM-assisted graph machine learning. |
| title | LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.09438 |