Summary of Learning Fair and Preferable Allocations Through Neural Network, by Ryota Maruo et al.
Learning Fair and Preferable Allocations through Neural Network
by Ryota Maruo, Koh Takeuchi, Hisashi Kashima
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 novel neural network-based approach to learning implicit resource allocation mechanisms that strictly satisfy fairness constraints, specifically envy-freeness up to one good (EF1). The authors design a neural round robin (NRR) model that parameterizes the classic round robin algorithm and can be trained to learn the agent ordering used for RR. The NRR model is built from a differentiable relaxation of RR and is demonstrated to outperform baselines in terms of proximity of predicted allocations and other metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to figure out how to divide things fairly when there’s not enough to go around. Right now, people use special rules or algorithms to make decisions about who gets what, but these can be tricky to understand mathematically. The authors want to create a way to learn from examples and make sure the allocations are fair. They built a new computer model that combines some old ideas with new techniques. This model can learn how to divide things fairly and do better than other methods. |
Keywords
» Artificial intelligence » Neural network
