Summary of Fairdgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning, by Wei Chen et al.
FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning
by Wei Chen, Meng Yuan, Zhao Zhang, Ruobing Xie, Fuzhen Zhuang, Deqing Wang, Rui Liu
First submitted to arxiv on: 23 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 new framework called FairDgcl to improve fairness in recommender systems by implementing high-quality data augmentation. The goal is to alleviate user-level unfairness by altering the skewed distribution of training data among various user groups. FairDgcl uses a dynamic graph adversarial contrastive learning framework that learns generating fair augmentation strategies in an adversarial style. The framework consists of two learnable models that generate contrastive views within a contrastive learning framework, which automatically fine-tunes the augmentation strategies. Theoretical analysis shows that FairDgcl can simultaneously generate enhanced representations that possess both fairness and accuracy. Experimental results on four real-world datasets demonstrate the effectiveness of the proposed framework. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making sure that recommendation systems are fair and don’t favor certain groups over others. This is a problem because some people might get bad recommendations just because of who they are, like their age or gender. Some other researchers tried to solve this by changing the way the data is prepared for training the model, but those methods didn’t always work well. The new method in this paper, called FairDgcl, uses a special kind of learning that can help make sure recommendations are fair and good at the same time. |
Keywords
» Artificial intelligence » Data augmentation
