AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Max-Margin Deep Generative Models for (Semi-)Supervised Learning

Chongxuan Li, Jun Zhu, Bo Zhang

TPAMI 2017 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 77 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add max-margin hat loss regularization on unlabeled data (ablation)Conv-MMCVA · MNIST (100 labels)error rate (%): 6.4 -> 1.24Improved
add label-balance regularization (ablation)Conv-MMCVA · MNIST (100 labels)error rate (%): reduce 0.2%Improved
replace Pegasos hinge classifier on VA with max-margin training jointly with the generative model (CNN)Conv-VA · MNIST (full labels)error rate (%): 1.35 -> 0.45Improved
replace Pegasos with max-margin joint learning (CNN)Conv-VA · SVHN (full labels)error rate (%): 25.3 -> 3.09Improved
replace Pegasos with max-margin joint learning (MLP)VA · MNIST (full labels)error rate (%): 1.04 -> 0.90Improved
raise margin weight C from 0 to 10^3 (ablation)Conv-MMVA · MNIST (full labels)error rate (%): 1.35 -> 0.45Improved
set C=1 instead of 0 (ablation)Conv-MMVA · MNIST (full labels)error rate (%): 1.35 -> 1.86Hurt
increase C from 0 to 10^4 (ablation)Conv-MMVA · MNIST (full labels)variational lower bound: -93.17 -> -112.12Hurt
increase C from 10^3 to 10^4 (ablation)Conv-MMVA · MNIST (full labels)error rate (%): 0.45 -> 0.43Improved
use max-margin DGM with inferred missing values instead of CNN on incomplete inputConv-MMVA · MNIST Rect 12x12 missingerror rate (%): 47.2 -> 15.9Improved
add max-margin to Conv-VA for imputation under rectangle missingConv-VA · MNIST Rect 12x12 missing (imputation)MSE: 0.1299 -> 0.1090Improved
add max-margin to Conv-VA for imputation under random pixel drop 0.2Conv-VA · MNIST Rand-Drop 0.2 (imputation)MSE: 0.0111 -> 0.0147Hurt

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