Meta-Transfer Learning Empowered Temporal Graph Networks for Cross-City Real Estate Appraisal

TL;DR

This work designs an Event-Triggered Temporal Graph Network to model the irregular spatiotemporal correlations between evolving real estate transactions, and proposes a Tri-Level Optimization Based Meta- Learning framework to adaptively re-weight training transaction instances from multiple source cities to mitigate negative transfer, and thus improve the cross-city knowledge transfer effectiveness.

Abstract

Real estate appraisal is important for a variety of endeavors such as real estate deals, investment analysis, and real property taxation. Recently, deep learning has shown great promise for real estate appraisal by harnessing substantial online transaction data from web platforms. Nonetheless, deep learning is data-hungry, and thus it may not be trivially applicable to enormous small cities with limited data. To this end, we propose Meta-Transfer Learning Empowered Temporal Graph Networks (MetaTransfer) to transfer valuable knowledge from multiple data-rich metropolises to the data-scarce city to improve valuation performance. Specifically, by modeling the ever-growing real estate transactions with associated residential communities as a temporal event heterogeneous graph, we first design an Event-Triggered Temporal Graph Network to model the irregular spatiotemporal correlations between evolving real estate transactions. Besides, we formulate the city-wide real estate appraisal as a multi-task dynamic graph link label prediction problem, where the valuation of each community in a city is regarded as an individual task. A Hypernetwork-Based Multi-Task Learning module is proposed to simultaneously facilitate intra-city knowledge sharing between multiple communities and task-specific parameters generation to accommodate the community-wise real estate price distribution. Furthermore, we propose a Tri-Level Optimization Based Meta- Learning framework to adaptively re-weight training transaction instances from multiple source cities to mitigate negative transfer, and thus improve the cross-city knowledge transfer effectiveness. Finally, extensive experiments based on five real-world datasets demonstrate the significant superiority of MetaTransfer compared with eleven baseline algorithms.

Figures (13)

• Figure 1: (a) Distribution of real estate transaction records volume of 293 Chinese cities, over 60$\%$ cities are with less than 1,000 records. (b) Illustration of the cross-city real estate appraisal task. The valuation performance in the data-scarce target city can be improved by transferring valuable knowledge from multiple data-rich source cities.
• Figure 2: The framework overview of MetaTransfer.
• Figure 3: Illustrations of the diversity between real estate price distributions of communities from cities Guangzhou and Mianyang, where different communities in a city are denoted by different colors.
• Figure 4: Ablation study. "M" and "S" denote Mianyang and Shaoxing, respectively.
• Figure 5: Effect of different source cities on cross-city knowledge transfer.