Summary of Fair Graph Neural Network with Supervised Contrastive Regularization, by Mahdi Tavassoli Kejani (ut3) et al.
Fair Graph Neural Network with Supervised Contrastive Regularization
by Mahdi Tavassoli Kejani, Fadi Dornaika, Jean-Michel Loubes
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 The paper proposes a novel framework for training fairness-aware Graph Neural Networks (GNNs) that addresses biases in node attributes and connections. The Counterfactual Augmented Fair Graph Neural Network Framework (CAF) is enhanced with Supervised Contrastive Loss and Environmental Loss to improve both accuracy and fairness. Experimental results on three real-world datasets show the superiority of the proposed model over existing graph-based learning methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making sure that computer programs are fair when they deal with graphs, like social networks or transportation systems. Right now, these programs can be biased because of the way they’re trained. The researchers propose a new way to train these programs so that they’re more fair and accurate. They tested their method on real-world data and showed that it’s better than other methods. |
Keywords
* Artificial intelligence * Contrastive loss * Graph neural network * Supervised
