# Task-Adaptive Meta-Learning Framework for Advancing Spatial Generalizability

arXiv: https://arxiv.org/abs/2212.06864 · HTML: https://mlsanity.com/paper/2212.06864/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 49 references that are in the map.
- First posted on arXiv 10 Dec 2022.

## Builds on (most cited first, 23 of 23)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [Few-Shot Image Recognition by Predicting Parameters from Activations](https://mlsanity.com/paper/1706.03466/) (2017)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Understanding and Improving Information Transfer in Multi-Task Learning](https://mlsanity.com/paper/2005.00944/) (2020)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [learn2learn: A Library for Meta-Learning Research](https://mlsanity.com/paper/2008.12284/) (2020)
- [Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles](https://mlsanity.com/paper/2001.11086/) (2020)
- [Efficient Continuous Pareto Exploration in Multi-Task Learning](https://mlsanity.com/paper/2006.16434/) (2020)
- [Machine Learning for the Geosciences: Challenges and Opportunities](https://mlsanity.com/paper/1711.04708/) (2017)
- [The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning](https://mlsanity.com/paper/2008.10857/) (2020)
- [DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection](https://mlsanity.com/paper/1510.05484/) (2015)
- [Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning](https://mlsanity.com/paper/2011.05369/) (2020)
- [Efficient Multitask Feature and Relationship Learning](https://mlsanity.com/paper/1702.04423/) (2017)
- [Wheat Crop Yield Prediction Using Deep LSTM Model](https://mlsanity.com/paper/2011.01498/) (2020)

## Built on by (most cited first, 7 of 7)

- [Foundation Models for Environmental Science: A Survey of Emerging Frontiers](https://mlsanity.com/paper/2504.04280/) (2025)
- [Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction](https://mlsanity.com/paper/2510.00268/) (2025)
- [Spatial Distribution-Shift Aware Knowledge-Guided Machine Learning](https://mlsanity.com/paper/2502.14840/) (2025)
- [Intention-Adaptive LLM Fine-Tuning for Text Revision Generation](https://mlsanity.com/paper/2602.00477/) (2026)
- [Heterogeneity-Aware Client Selection Methodology For Efficient Federated Learning](https://mlsanity.com/paper/2602.20450/) (2026)
- [Retrieval-Augmented Multi-scale Framework for County-Level Crop Yield Prediction Across Large Regions](https://mlsanity.com/paper/2603.07305/) (2026)
- [Evaluating and improving crop-yield forecasting methods during extreme drought](https://mlsanity.com/paper/2608.17971/) (2026)

## Abstract (arXiv)

Spatio-temporal machine learning is critically needed for a variety of societal applications, such as agricultural monitoring, hydrological forecast, and traffic management. These applications greatly rely on regional features that characterize spatial and temporal differences. However, spatio-temporal data often exhibit complex patterns and significant data variability across different locations. The labels in many real-world applications can also be limited, which makes it difficult to separately train independent models for different locations. Although meta learning has shown promise in model adaptation with small samples, existing meta learning methods remain limited in handling a large number of heterogeneous tasks, e.g., a large number of locations with varying data patterns. To bridge the gap, we propose task-adaptive formulations and a model-agnostic meta-learning framework that ensembles regionally heterogeneous data into location-sensitive meta tasks. We conduct task adaptation following an easy-to-hard task hierarchy in which different meta models are adapted to tasks of different difficulty levels. One major advantage of our proposed method is that it improves the model adaptation to a large number of heterogeneous tasks. It also enhances the model generalization by automatically adapting the meta model of the corresponding difficulty level to any new tasks. We demonstrate the superiority of our proposed framework over a diverse set of baselines and state-of-the-art meta-learning frameworks. Our extensive experiments on real crop yield data show the effectiveness of the proposed method in handling spatial-related heterogeneous tasks in real societal applications.