Summary of Toward Structure Fairness in Dynamic Graph Embedding: a Trend-aware Dual Debiasing Approach, by Yicong Li et al.
Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach
by Yicong Li, Yu Yang, Jiannong Cao, Shuaiqi Liu, Haoran Tang, Guandong Xu
First submitted to arxiv on: 19 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 recent breakthrough in graph learning has led to structurally fair static graph embeddings, but dynamic graphs have remained a challenge. To address this issue, researchers proposed FairDGE, the first algorithm to learn structurally fair dynamic graph embeddings. This novel approach jointly embeds connection changes among vertices and the long-term evolutionary trend of vertex degrees, while also incorporating a dual debiasing strategy to customize fairness for different biased structural evolutions. The resulting algorithm achieves both improved effectiveness and fairness in embedding performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, scientists have been trying to figure out how to make graph learning fair when the graphs change over time. Right now, we can only do this for static graphs, but it’s a big problem because real-world data is often dynamic. To solve this issue, the researchers developed an algorithm called FairDGE that can learn from changing graphs and make sure the results are fair. They did this by looking at how vertex degrees change over time and using that information to create better embeddings. This new approach helps both the accuracy and fairness of graph learning. |
Keywords
* Artificial intelligence * Embedding
