UME: A Unified Meta-Generalization Framework for Cross-Domain ETA

2026-05-30

AI Summary

This work addresses the challenges of zero-shot generalization, inconsistent feature spaces, and missing structured features in ETA prediction during the cold-start phase of cross-border on-demand logistics. To tackle these issues, the authors propose UME, a unified meta-generalization framework that employs a dual-branch architecture and a hypernetwork-driven meta-learning mechanism. UME integrates domain-level priors with instance-level context through dynamic feature gating, expert attention mechanisms, and knowledge distillation to enable effective cross-domain collaborative modeling. Notably, UME is the first framework capable of performing zero-shot ETA prediction for cold-start domains while uniformly handling both new and mature domains, thereby overcoming limitations imposed by missing features. Extensive offline evaluations and online A/B tests on Meituan’s Keeta international delivery platform demonstrate that UME significantly outperforms existing baselines.

Abstract

Accurate Estimated Time of Arrival (ETA) prediction on checkout page is crucial in instant logistics for enhancing user satisfaction, optimizing dispatching, and controlling operational costs. In international on-demand delivery platforms, where ETA data originates from diverse countries or regions with different patterns, multi-domain modeling is of great importance and has been widely adopted. However, existing methods still face three critical challenges in real-world deployment. First, current multi-domain models struggle to generalize to completely unseen domains, failing to achieve zero-shot prediction during the initial cold-start phase. Second, cross-domain feature spaces are often assumed to be consistent, whereas new domains commonly suffer from structural missingness of offline (statistical) features due to the lack of historical data. Third, such feature missingness often compels industrial systems to model mature and cold-start domains separately, hindering knowledge transfer and increasing maintenance overhead. To address these challenges, we propose \textbf{UME}, a \textbf{U}nified \textbf{M}eta-generalization framework for \textbf{E}TA. Specifically, UME integrates a unified dual-branch architecture with a novel meta-learning mechanism that employs a hypernetwork-based meta learner. By leveraging domain-level knowledge and instance-level context, the meta learner empowers three meta modules to dynamically modulate feature gating, expert attention, and final prediction, capturing cross-domain correlations and facilitating intra-domain adaptation. A knowledge distillation strategy is further introduce to enhance performance. UME has now been deployed in Meituan-keeta delivery platform (the largest international food delivery platform in China). Extensive offline experiments and online A/B tests demonstrate that UME significantly outperforms existing baselines.

Problem

• cross-domain ETA
• zero-shot prediction
• feature missingness
• cold-start
• multi-domain modeling

Innovation

• meta-learning
• cross-domain generalization
• zero-shot prediction
• hypernetwork
• knowledge distillation