Summary of F-fomaml: Gnn-enhanced Meta-learning For Peak Period Demand Forecasting with Proxy Data, by Zexing Xu et al.
F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data
by Zexing Xu, Linjun Zhang, Sitan Yang, Rasoul Etesami, Hanghang Tong, Huan Zhang, Jiawei Han
First submitted to arxiv on: 23 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR); Econometrics (econ.EM); Methodology (stat.ME)
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 proposed approach leverages strategically chosen proxy data from non-peak periods, enriched by features learned from a graph neural networks (GNNs)-based forecasting model, to predict demand during peak events. The method formulates demand prediction as a meta-learning problem and develops the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm that learns feature-specific layer parameters. This approach achieves improved generalization by considering domain similarities through task-specific metadata. Theoretically, the excess risk decreases as the number of training tasks increases. The empirical evaluations on large-scale industrial datasets demonstrate the superiority of this approach. Compared to existing state-of-the-art models, the method reduces the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on a publicly accessible JD.com dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Demand prediction is important for e-commerce and retail businesses during peak sales events. Traditional methods struggle due to limited historical data from these periods. The paper proposes a new approach that uses proxy data from non-peak periods, along with features learned from a graph neural networks (GNNs) forecasting model, to predict demand during peak events. The method is designed for meta-learning and develops the F-FOMAML algorithm. This helps the model generalize well by considering domain similarities through task-specific metadata. The paper shows that this approach works well in practice and improves accuracy compared to other methods. |
Keywords
» Artificial intelligence » Generalization » Meta learning
