aiqbench analysis
This research investigates how spatially biased sampling disrupts standard semi-supervised learning assumptions, revealing a sudden performance threshold rather than gradual degradation when distribution mismatch becomes severe. The study introduces diagnostic tools to detect these failures and highlights that models often become dangerously overconfident in regions lacking labeled data due to spatial non-stationarity. These findings are critical for deploying robust AI systems in geospatial applications where label collection is inherently uneven.
Semi-Supervised Learning under Spatially Biased Sampling
arXiv:2609.07982v1 Announce Type: new Abstract: Standard semi-supervised learning (SSL) typically relies on labelled and unlabelled data sharing a common marginal distribution. This assumption is often violated by biased spatial sampling mechanism, when labels are collected under spatially biased or preferential site selection. We treat this marginal mismatch, spatial autocorrelation, and spatial non-stationarity as three distinct mechanisms, varied independently via a labelled-sampling concentration parameter, a spatial length scale, and a non-stationarity strength parameter, and ask how mismatch degrades SSL, whether the cluster and manifold assumptions survive it, and how the resulting failure can be diagnosed. Using a controlled synthetic framework alongside PovertyMap-WILDS, California housing, socio-economic and US air quality monitoring datasets, we systematically vary the degree of mismatch while accounting for spatial autocorrelation and non-stationarity. Through a series of analyses including a segmented-regression changepoint, we show that in the synthetic generator, SSL performance does not degrade gradually but instead exhibits a threshold-like breakdown between approximately 0.71 and 0.77 once distribution mismatch becomes sufficiently severe. We further demonstrate that spatial non-stationarity contributes to performance loss independently of marginal mismatch and that models become increasingly overconfident outside the regions where labels are available. To support practical deployment, we evaluate several distribution-divergence measures as indicators of reliability and introduce a kernel-weighted local divergence metric that provides a more stable estimate of spatial mismatch than a na\"ive localised approach. These findings provide empirical evidence and diagnostic tools for better documenting the risk of incorporating unlabelled spatial data into semi-supervised learning workflows.
Abstract:Standard semi-supervised learning (SSL) typically relies on labelled and unlabelled data sharing a common marginal distribution. This assumption is often violated by biased spatial sampling mechanism, when labels are collected under spatially biased or preferential site selection. We treat this marginal mismatch, spatial autocorrelation, and spatial non-stationarity as three distinct mechanisms, varied independently via a labelled-sampling concentration parameter, a spatial length scale, and a non-stationarity strength parameter, and ask how mismatch degrades SSL, whether the cluster and manifold assumptions survive it, and how the resulting failure can be diagnosed. Using a controlled synthetic framework alongside PovertyMap-WILDS, California housing, socio-economic and US air quality monitoring datasets, we systematically vary the degree of mismatch while accounting for spatial autocorrelation and non-stationarity. Through a series of analyses including a segmented-regression changepoint, we show that in the synthetic generator, SSL performance does not degrade gradually but instead exhibits a threshold-like breakdown between approximately 0.71 and 0.77 once distribution mismatch becomes sufficiently severe. We further demonstrate that spatial non-stationarity contributes to performance loss independently of marginal mismatch and that models become increasingly overconfident outside the regions where labels are available. To support practical deployment, we evaluate several distribution-divergence measures as indicators of reliability and introduce a kernel-weighted local divergence metric that provides a more stable estimate of spatial mismatch than a naïve localised approach. These findings provide empirical evidence and diagnostic tools for better documenting the risk of incorporating unlabelled spatial data into semi-supervised learning workflows.
26 pages, 9 figures, 9 tables. Supplementary material included as an ancillary file
Machine Learning (cs.LG)
J.2; I.5.1; I.6.6
arXiv:2609.07982 [cs.LG]
(or arXiv:2609.07982v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.07982 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
supplementary.pdf
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 352 words
Related coverage
Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations
arXiv · Jul 21, 2026
Label-Efficient Learning for Ground-Based Sky-Image Classification: A Benchmark of Transfer Learning, Active Learning, and Pseudo-Labeling on GCD
arXiv · Sep 23, 2026
Representation Learning for Sample-Efficient CATE Estimation by Leveraging Multiple Outcomes
arXiv · Sep 9, 2026
Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges
arXiv · Aug 24, 2026