Task-Adaptive Meta-Learning Framework for Advancing Spatial
Generalizability
- URL: http://arxiv.org/abs/2212.06864v1
- Date: Sat, 10 Dec 2022 01:50:35 GMT
- Title: Task-Adaptive Meta-Learning Framework for Advancing Spatial
Generalizability
- Authors: Zhexiong Liu, Licheng Liu, Yiqun Xie, Zhenong Jin, Xiaowei Jia
- Abstract summary: We propose a model-agnostic meta-learning framework that ensembles regionally heterogeneous data into location-sensitive meta tasks.
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.
- Score: 5.448577641039577
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 are often complex and pose several unique challenges for machine learning
models: 1) multiple models are needed to handle region-based data patterns that
have significant spatial heterogeneity across different locations; 2) local
models trained on region-specific data have limited ability to adapt to other
regions that have large diversity and abnormality; 3) spatial and temporal
variations entangle data complexity that requires more robust and adaptive
models; 4) limited spatial-temporal data in real scenarios (e.g., crop yield
data is collected only once a year) makes the problems intrinsically
challenging. To bridge these gaps, 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.
Related papers
- One Fits All: General Mobility Trajectory Modeling via Masked Conditional Diffusion [11.373845190033297]
Trajectory data play a crucial role in many applications, ranging from network optimization to urban planning.
Existing studies on trajectory data are task-specific, and their applicability is limited to the specific tasks on which they have been trained, such as generation, recovery, or prediction.
We propose a general trajectory modeling framework via conditional diffusion (named GenMove)
Our model significantly outperforms state-of-the-art baselines, with the highest performance exceeding 13% improvement in generation tasks.
arXiv Detail & Related papers (2025-01-23T03:13:45Z) - Collaborative Imputation of Urban Time Series through Cross-city Meta-learning [54.438991949772145]
We propose a novel collaborative imputation paradigm leveraging meta-learned implicit neural representations (INRs)
We then introduce a cross-city collaborative learning scheme through model-agnostic meta learning.
Experiments on a diverse urban dataset from 20 global cities demonstrate our model's superior imputation performance and generalizability.
arXiv Detail & Related papers (2025-01-20T07:12:40Z) - NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks [5.852777557137612]
We introduce a synthetic mobility dataset, NUMOSIM, that provides a controlled, ethical, and diverse environment for anomaly benchmarking techniques.
NUMOSIM simulates a wide array of realistic mobility scenarios, encompassing both typical and anomalous behaviours.
We provide open access to the NUMOSIM dataset, along with comprehensive documentation, evaluation metrics, and benchmark results.
arXiv Detail & Related papers (2024-09-04T18:31:24Z) - A Practitioner's Guide to Continual Multimodal Pretraining [83.63894495064855]
Multimodal foundation models serve numerous applications at the intersection of vision and language.
To keep models updated, research into continual pretraining mainly explores scenarios with either infrequent, indiscriminate updates on large-scale new data, or frequent, sample-level updates.
We introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements.
arXiv Detail & Related papers (2024-08-26T17:59:01Z) - SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities [55.87169702896249]
Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift.
We present a complete and fair evaluation of existing shallow algorithms, including reweighting, mapping, and subspace alignment.
Our benchmark highlights the importance of realistic validation and provides practical guidance for real-life applications.
arXiv Detail & Related papers (2024-07-16T12:52:29Z) - SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation [62.889835139583965]
We introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data.
As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data.
Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real scenarios.
arXiv Detail & Related papers (2023-04-06T17:36:23Z) - Heterogeneous Domain Adaptation and Equipment Matching: DANN-based
Alignment with Cyclic Supervision (DBACS) [3.4519649635864584]
This work introduces the Domain Adaptation Neural Network with Cyclic Supervision (DBACS) approach.
DBACS addresses the issue of model generalization through domain adaptation, specifically for heterogeneous data.
This work also includes subspace alignment and a multi-view learning that deals with heterogeneous representations.
arXiv Detail & Related papers (2023-01-03T10:56:25Z) - One-Shot Domain Adaptive and Generalizable Semantic Segmentation with
Class-Aware Cross-Domain Transformers [96.51828911883456]
Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data.
Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation.
We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
arXiv Detail & Related papers (2022-12-14T15:54:15Z) - DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based
Localization [27.294822556484345]
Long-term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics.
We propose a novel multi-task architecture to fuse the geometric and semantic information into the multi-scale latent embedding representation for visual place recognition.
arXiv Detail & Related papers (2020-10-01T17:44:25Z) - Meta-Learning for Few-Shot Land Cover Classification [3.8529010979482123]
We evaluate the model-agnostic meta-learning (MAML) algorithm on classification and segmentation tasks.
We find that few-shot model adaptation outperforms pre-training with regular gradient descent.
This indicates that model optimization with meta-learning may benefit tasks in the Earth sciences.
arXiv Detail & Related papers (2020-04-28T09:42:41Z) - Dynamic Federated Learning [57.14673504239551]
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments.
We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data.
Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
arXiv Detail & Related papers (2020-02-20T15:00:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.