Summary of Lpnl: Scalable Link Prediction with Large Language Models, by Baolong Bi et al.
LPNL: Scalable Link Prediction with Large Language Models
by Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Xueqi Cheng
First submitted to arxiv on: 24 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A framework called LPNL (Link Prediction via Natural Language) is introduced to scale up link prediction on large-scale heterogeneous graphs using large language models (LLMs). The approach utilizes novel prompts that describe graph details in natural language, a two-stage sampling pipeline to extract key information from the graphs, and a divide-and-conquer strategy to manage input tokens. A T5 model is fine-tuned for link prediction through self-supervised learning. Experimental results show LPNL outperforming advanced baselines on large-scale graph tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Link prediction on big graphs is a tricky task because there’s so much information to process. Researchers came up with a new way to do this using language models. They created special prompts that explain the graph in simple language and used a special pipeline to focus on important details. They even trained a model specifically for link prediction. The results show that their approach works better than other methods on big graphs. |
Keywords
* Artificial intelligence * Self supervised * T5
