Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916155460943872 |
|---|---|
| author | Zhang, Xin Zhang, Linhai Zhou, Deyu Xu, Guoqiang |
| author_facet | Zhang, Xin Zhang, Linhai Zhou, Deyu Xu, Guoqiang |
| contents | Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels. Recently, the emergence of LLMs has introduced new solutions to such problems by leveraging graph structures to generate supplementary user profiles. However, previous approaches have not fully utilized the graph understanding capabilities of LLMs and have struggled to adapt to complex streaming data environments. In this work, we propose a fine-grained streaming data synthesis framework that categorizes sparse users into three categories: Mid-tail, Long-tail, and Extreme. Specifically, we design LLMs to comprehensively understand three key graph elements in streaming data, including Local-global Graph Understanding, Second-Order Relationship Extraction, and Product Attribute Understanding, which enables the generation of high-quality synthetic data to effectively address sparsity across different categories. Experimental results on three real datasets demonstrate significant performance improvements, with synthesized data contributing to MSE reductions of 45.85%, 3.16%, and 62.21%, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06139 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity Zhang, Xin Zhang, Linhai Zhou, Deyu Xu, Guoqiang Computation and Language Artificial Intelligence Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels. Recently, the emergence of LLMs has introduced new solutions to such problems by leveraging graph structures to generate supplementary user profiles. However, previous approaches have not fully utilized the graph understanding capabilities of LLMs and have struggled to adapt to complex streaming data environments. In this work, we propose a fine-grained streaming data synthesis framework that categorizes sparse users into three categories: Mid-tail, Long-tail, and Extreme. Specifically, we design LLMs to comprehensively understand three key graph elements in streaming data, including Local-global Graph Understanding, Second-Order Relationship Extraction, and Product Attribute Understanding, which enables the generation of high-quality synthetic data to effectively address sparsity across different categories. Experimental results on three real datasets demonstrate significant performance improvements, with synthesized data contributing to MSE reductions of 45.85%, 3.16%, and 62.21%, respectively. |
| title | Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.06139 |