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

TL;DR

This paper introduces MetaTransfer, a novel meta-transfer learning approach using temporal graph networks to improve real estate valuation in data-scarce cities by transferring knowledge from data-rich metropolises.

Contribution

The paper proposes a new MetaTransfer framework combining temporal graph modeling, multi-task learning, and meta-learning to enhance cross-city real estate appraisal performance.

Findings

MetaTransfer outperforms eleven baseline algorithms in experiments.

The approach effectively transfers knowledge from large to small cities.

Significant improvements in valuation accuracy demonstrated across five real-world datasets.

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 Powered 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.