AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Robust-by-Design Distributional Learning from Contaminated Samples

Nevena Gligić, Arya Farahi

NeurIPS 2026 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 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 robust distributional learning framework that recovers the target distribution from contaminated mixed samples without discarding most of the data, as stated in the abstract.

Problem

Distributional learning from observed samples that are contaminated mixtures of the target population (e.g., from retrieval, scraping, automated filtering), where standard objectives either converge to the wrong target or discard most data.

Approach

Designs distributional objectives that are robust by construction to contamination, using the full contaminated sample rather than only a small trusted subset; details beyond the abstract are unavailable.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add audit-based residual correction to the MMD objective instead of using naive MMD on the contaminated poolMMD-based linear regression · Contaminated linear regressionl2 error: 0.259 -> 0.110Improved
use full pool with corrected objective instead of audit-only training (ablation)CC-MMD regression · Contaminated linear regressionl2 error: 0.169 -> 0.110Improved
use bounded-kernel MMD instead of squared error or robust losses (Huber, Tukey)Regression under contamination · Contaminated linear regressionl2 error: 0.733 -> 0.259 (Tukey vs naive MMD)Improved
use Huber or Tukey robust losses instead of MSERegression under contamination · Concrete strength prediction (epsilon=0.6)test MSE: 0.76 -> 0.77 (Huber), 0.95 (Tukey)No clear effect
use CC-MMD instead of next-best baseline at high contaminationMLP regressor · Concrete strength prediction (epsilon=0.5)test MSE: 34% reduction at epsilon=0.5; 25% at epsilon=0.6Improved
use CC-MMD at no contaminationMLP regressor · Concrete strength prediction (epsilon=0)test MSENo clear effect
use CC-MMD instead of naive MMDIAF generator on MNIST with contamination · MNIST generation, epsilon=0.8test MMD^2: 0.046 -> 0.00371Improved
use CC-MMD instead of ELBO or adversarial trainingVAE and GMMN on MNIST with K-MNIST contamination · MNIST generation, epsilon=0.60FIDMixed
use CC-MMD instead of audit-only training at very high contamination (ablation)IAF generator · MNIST generation, contamination sweeptest MMD^2Mixed
increase audit size (ablation)CC-MMD · MNIST generation (audit-size ablation)test MMD^2 / FIDImproved
increase proxy AUROC (ablation)CC-MMD · MNIST generation (proxy-quality ablation)test MMD^2 / FIDImproved

Experimental setup

Baselines: standard distributional objectives trusted-subset training

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