Pith. sign in

REVIEW 1 cited by

Adapting to Shifting Correlations with Unlabeled Data Calibration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.05996 v1 pith:LTVINVI5 submitted 2024-09-09 cs.LG

classification cs.LG
keywords featuressitesunstablecorrelationsaccuracyconfoundershowevermethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that are stable across sites and discard unstable features. However, unstable features might have complementary information that, if used appropriately, could increase accuracy. More recent methods try to adapt to unstable features at the new sites to achieve higher accuracy. However, they make unrealistic assumptions or fail to scale to multiple confounding features. We propose Generalized Prevalence Adjustment (GPA for short), a flexible method that adjusts model predictions to the shifting correlations between prediction target and confounders to safely exploit unstable features. GPA can infer the interaction between target and confounders in new sites using unlabeled samples from those sites. We evaluate GPA on several real and synthetic datasets, and show that it outperforms competitive baselines.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving realistic semi-supervised learning with doubly robust estimation

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Doubly robust estimation of the unlabeled class distribution improves pseudo-labeling methods for realistic long-tailed semi-supervised learning.

Pith tools