Summary of Enhancing Cross-domain Link Prediction Via Evolution Process Modeling, by Xuanwen Huang et al.
Enhancing Cross-domain Link Prediction via Evolution Process Modeling
by Xuanwen Huang, Wei Chow, Yize Zhu, Yang Wang, Ziwei Chai, Chunping Wang, Lei Chen, Yang Yang
First submitted to arxiv on: 3 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 DyExpert is a novel dynamic graph model designed for cross-domain link prediction. This approach explicitly models historical evolving processes to learn the evolution pattern of specific downstream graphs and make pattern-specific predictions. The model utilizes a decode-only transformer, enabling efficient parallel training and inference through conditioned link generation that integrates evolution modeling and link prediction. DyExpert is trained on extensive dynamic graphs across diverse domains, including 6 million dynamic edges. Experimental results demonstrate state-of-the-art performance in cross-domain link prediction, with an average improvement of 11.40% Average Precision across eight untrained graphs compared to advanced baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary DyExpert is a new way to predict connections between things on different scales. It helps us understand how patterns change over time by looking at what happened before. This model uses special computer code to make predictions and can do many calculations at the same time. DyExpert was tested on lots of different data and performed better than other methods. It’s especially good at making predictions when there isn’t much information available. |
Keywords
* Artificial intelligence * Inference * Precision * Transformer
