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

Source: [Max-Margin Deep Generative Models for (Semi-)Supervised Learning](<https://www.sota2.com/research/paper/68fa63001e209131ce9fc357>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:31:19.733Z

Authors: Chongxuan Li, Jun Zhu, Bo Zhang

Published: 2016-11-22T01:36:29.000Z

## Abstract

Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, it is relatively insufficient to empower the discriminative ability of DGMs on making accurate predictions. This paper presents max-margin deep generative models (mmDGMs) and a class-conditional variant (mmDCGMs), which explore the strongly discriminative principle of max-margin learning to improve the predictive performance of DGMs in both supervised and semi-supervised learning, while retaining the generative capability. In semi-supervised learning, we use the predictions of a max-margin classifier as the missing labels instead of performing full posterior inference for efficiency; we also introduce additional max-margin and label-balance regularization terms of unlabeled data for effectiveness. We develop an efficient doubly stochastic subgradient algorithm for the piecewise linear objectives in different settings. Empirical results on various datasets demonstrate that: (1) max-margin learning can significantly improve the prediction performance of DGMs and meanwhile retain the generative ability; (2) in supervised learning, mmDGMs are competitive to the best fully discriminative networks when employing convolutional neural networks as the generative and recognition models; and (3) in semi-supervised learning, mmDCGMs can perform efficient inference and achieve state-of-the-art classification results on several benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on SVHN 1,000 labels (train)](<https://www.sota2.com/research/sota/image-classification-on-svhn-1-000-labels-train.md>): Image Classification; SVHN 1,000 labels (train); Error Rate (%): 4.95.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1611.07119>)

[PDF](<https://arxiv.org/pdf/1611.07119.pdf>)