cs.LGNov 8, 2026

Boundary Mass in Feature Space as a Label-Budget Diagnostic for Representations

Authors: Siming Zhang, Zhehui Shen, Shijie Chen, Yansen Yu, Hang Yu

Organizations: Shanghai University

Abstract

Low-label transfer is often decided by a practical question: after a representation looks useful, how many labels are still needed to learn the downstream boundary? Transferability and probe-quality scores characterize global alignment, likelihood, margins, and calibration. Boundary-near target mass complements these diagnostics by measuring the ambiguous regions where scarce labels are most costly. We propose effective boundary complexity, a label-budget diagnostic for frozen representations and linear probes. It measures mass in a thin strip around the learned boundary and normalizes it by class balance, so dense ambiguous regions and predicted-class imbalance are both counted. We prove that, under a smooth representation map, density change and tangential surface change cancel at first order, leaving boundary-normal stretch or compression as the governing factor. This yields a cached-feature estimator that fits a probe on one split and counts independent held-out features near its boundary. Experiments support the diagnostic at three levels. Controlled transformations match the predicted law across 74 maps with 0.38% median relative error. On real frozen features, normal-direction changes move both measured boundary mass and label demand, while tangent controls preserve the first-order coefficient. A differentiable surrogate reduces measured complexity by 16-36% at matched top-1 utility. Finally, CIFAR-100 and Tiny-ImageNet experiments support boundary mass as a second-stage diagnostic for near-tied representations. Five-way experiments show strong OvR-interface backbone-ranking agreement (Spearman 0.872), while acquisition experiments show high correlations between initial boundary mass and realized label budgets across three sampling policies (0.779-0.830). Code is available at https://github.com/qqaqq-code/boundary_mass.

Figures & tables

Appendix figures & tables39 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Task Scarcity and Label Leakage in Relational Transfer Learning

    Mar 31, 2026Francisco Galuppo Azevedo, Clarissa Lima Loures, Denis Oliveira Correalabel leakageTransfer Learning

  2. A Comparative Study of Label-free Representation Quality Metrics in Deep Learning

    Aug 24, 2026Daniel Richards Arputharaj, Daniel Jönsson, Gabriel EilertsenReference-Free EvaluationVisual Representation Learning