Summary of Explainable Hierarchical Urban Representation Learning For Commuting Flow Prediction, by Mingfei Cai et al.
Explainable Hierarchical Urban Representation Learning for Commuting Flow Prediction
by Mingfei Cai, Yanbo Pang, Yoshihide Sekimoto
First submitted to arxiv on: 27 Aug 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 The paper proposes a heterogeneous graph-based model for commuting flow prediction at large scales, such as prefectures or nations. By leveraging region representation learning and preserving ranked structures, the model generates meaningful embeddings at multiple spatial resolutions for predicting different types of OD flows. The proposed method is tested using real-world aggregated mobile phone datasets from Shizuoka Prefecture, Japan, and outperforms existing models in terms of a uniform urban structure. This work extends our understanding of predicted results by providing reasonable explanations to enhance the credibility of the model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Commuting flow prediction helps cities make better decisions. Right now, there are limited ways to predict this information accurately. Researchers have developed ways to learn from different data sources, but they haven’t explained how these different pieces fit together. Cities and their districts naturally have a hierarchy, which makes understanding relationships between them important. This paper creates a new model that uses graphs to represent cities at different levels and predicts commuting flows. It tests this model using real data from Japan and shows it performs better than existing methods. |
Keywords
» Artificial intelligence » Representation learning
