AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

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

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a boundary-mass diagnostic in feature space that estimates how much target data lies near the fitted decision boundary, as a label-budget indicator for representations.

Problem

Predicting how many labels are needed to learn a downstream decision boundary in low-label transfer; existing transferability and probe-quality scores (global alignment, likelihood, margins, calibration) do not measure target mass near the boundary where labels are most costly.

Approach

Introduces an effective boundary-mass score measuring how much target data remains close to the fitted decision boundary in feature space, used as a diagnostic of label budget rather than global alignment or calibration.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
expand features along the boundary normal (s=1 to s=2) (ablation)frozen CIFAR-100 features with linear probe · CIFAR-100 label budgetbudget (spc): -1.54 spc; AULC +2.26Improved
scale features along a tangent direction (s=1 to s=2) (ablation)frozen CIFAR-100 features · CIFAR-100 label budgetbudget (spc): +0.02 spc; AULC -0.22No clear effect
add smooth boundary-mass penalty to linear head traininglinear head on frozen features · CIFAR-100 / Tiny-ImageNetboundary complexity and top-1: psi 201.68 -> 169.22; top-1 53.97 -> 53.84Improved
add top-2 boundary-pressure regularizer to ResNet-18 trainingResNet-18 · CIFAR-100Top-1: 53.68 -> 57.09Improved
use weight decay, margin or entropy regularization instead of boundary pressure (ablation)ResNet-18 · CIFAR-100boundary estimate: 23.57 -> 23.61 (weight decay)No clear effect
add boundary mass to conventional and transferability diagnostics (ablation)label-budget regression · CIFAR-100 binary pairsR^2: 0.734 -> 0.749Improved
second-stage tie-break by boundary mass among two shortlisted backbonesbackbone selection · CIFAR-100 binary pairsregret (spc): 0.058 -> 0.030Improved
normalize sample size by psi_eff in sample-complexity fit (ablation)plug-in boundary study · controlled syntheticR^2: 0.698 -> 0.895Improved
use uncertainty/hybrid acquisition instead of random (ablation)label acquisition · CIFAR-100 binarymean realized budget (spc): 7.05 -> 5.57 / 5.47Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy