提出新型无向生成模型JRF，解决半监督学习中生成与分类的矛盾
Joint-stochastic-approximation Random Fields with Application to Semi-supervised Learning
- 设计联合随机逼近随机场，构建新型无向生成模型
- 在MNIST/SVHN/CIFAR-10上实现生成与分类双优，性能达顶尖水平
- 适合需兼顾生成质量与分类精度的半监督学习研究者
我们研究了用于半监督学习（SSL）的深度生成模型（DGMs），主要包括生成对抗网络（GANs）和变分自编码器（VAEs），发现两个问题：第一，生成过程中存在模式缺失和模式覆盖现象；第二，使用有向生成模型时，良好分类与良好生成之间存在尴尬冲突。为解决这些问题，我们正式提出了联合随机逼近随机场（JRFs）——一种构建深度无向生成模型的新方法，适用于半监督学习。合成实验表明，JRFs能有效平衡模式覆盖与模式缺失，较好拟合真实数据分布。实证结果表明，JRFs在广泛使用的数据集MNIST、SVHN和CIFAR-10上实现了与最先进方法相当的分类性能，同时具备良好的生成能力。
原文摘要 · Abstract (English)
Our examination of deep generative models (DGMs) developed for semi-supervised learning (SSL), mainly GANs and VAEs, reveals two problems. First, mode missing and mode covering phenomenons are observed in genertion with GANs and VAEs. Second, there exists an awkward conflict between good classification and good generation in SSL by employing directed generative models. To address these problems, we formally present joint-stochastic-approximation random fields (JRFs) -- a new family of algorithms for building deep undirected generative models, with application to SSL. It is found through synthetic experiments that JRFs work well in balancing mode covering and mode missing, and match the empirical data distribution well. Empirically, JRFs achieve good classification results comparable to the state-of-art methods on widely adopted datasets -- MNIST, SVHN, and CIFAR-10 in SSL, and simultaneously perform good generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。