paper-with-me

Papers

Semi-supervised Sequential Generative Models

2020-06-30 · Michael Teng, Tuan Anh Le, Adam Scibior, Frank Wood

We introduce a novel objective for training deep generative time-series models with discrete latent variables for which supervision is only sparsely available. This instance of semi-supervised learning is challenging for existing methods, because the exponential number of possible discrete latent configurations results in high variance gradient estimators. We first overcome this problem by extending the standard semi-supervised generative modeling objective with reweighted wake-sleep. However, we find that this approach still suffers when the frequency of available labels varies between training sequences. Finally, we introduce a unified objective inspired by teacher-forcing and show that this approach is robust to variable length supervision. We call the resulting method caffeinated wake-sleep (CWS) to emphasize its additional dependence on real data. We demonstrate its effectiveness with experiments on MNIST, handwriting, and fruit fly trajectory data.

📄 PDF Abstract BibTeX arXiv:2007.00155

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

A Probabilistic Semi-Supervised Approach with Triplet Markov Chains

2023-09-07 · Katherine Morales, Yohan Petetin

Triplet Markov chains are general generative models for sequential data which take into account three kinds of random variables: (noisy) observations, their associated discrete labels and latent variables which aim at st…

Bayesian InferenceTriplet

Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks

2023-08-27 · Xin Yang, Yi Lin, Zhiwei Wang, Xin Li 외

In this paper, we propose a bi-modality medical image synthesis approach based on sequential generative adversarial network (GAN) and semi-supervised learning. Our approach consists of two generative modules that synthes…

Generative Adversarial NetworkImage Generation

Hypernetworks for Continual Semi-Supervised Learning

2021-10-05 · Dhanajit Brahma, Vinay Kumar Verma, Piyush Rai

Learning from data sequentially arriving, possibly in a non i.i.d. way, with changing task distribution over time is called continual learning. Much of the work thus far in continual learning focuses on supervised learni…

Continual LearningGenerative Adversarial NetworkSplit-CIFAR-10

Semantic Parsing with Semi-Supervised Sequential Autoencoders

2016-09-29 · EMNLP 2016 11 · Tomáš Kočiský, Gábor Melis, Edward Grefenstette, Chris Dyer 외

We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical fo…

Semantic Parsing

Variational Sequential Labelers for Semi-Supervised Learning

2019-06-23 · EMNLP 2018 10 · Mingda Chen, Qingming Tang, Karen Livescu, Kevin Gimpel

We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent…

Learning Word EmbeddingsWord Embeddings