paper-with-me

홈 › Papers

Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs

2022-09-26 · Đorđe Miladinović, Kumar Shridhar, Kushal Jain, Max B. Paulus, Joachim M. Buhmann, Mrinmaya Sachan, Carl Allen

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoders can often explain the data without utilizing the latent space, known as posterior collapse. To mitigate this, state-of-the-art models weaken the powerful decoder by applying uniformly random dropout to the decoder input. We show theoretically that this removes pointwise mutual information provided by the decoder input, which is compensated for by utilizing the latent space. We then propose an adversarial training strategy to achieve information-based stochastic dropout. Compared to uniform dropout on standard text benchmark datasets, our targeted approach increases both sequence modeling performance and the information captured in the latent space.

📄 PDF Abstract BibTeX arXiv:2209.12590

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderRepresentation Learning

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors

2018-12-21 · CVPR 2019 6 · Yedid Hoshen, Jitendra Malik

Unconditional image generation has recently been dominated by generative adversarial networks (GANs). GAN methods train a generator which regresses images from random noise vectors, as well as a discriminator that attemp…

Image GenerationUnconditional Image Generation

Generative Modeling of Bach-Style Symbolic Music: A Comparative Study of Autoregressive, Latent-Variable, and Adversarial Approaches

2026-06-11 · Dezhi Yu, Kyuil Lee, Yongkang Huang arxiv

We study generative modeling of Bach-style symbolic piano music using a shared MIDI corpus and three model families: autoregressive LSTMs with attention, latent-variable models including recurrent VAEs and vector-quantiz…

Music Generation

Natural Language Generation with Neural Variational Models

2018-08-27 · Hareesh Bahuleyan

In this thesis, we explore the use of deep neural networks for generation of natural language. Specifically, we implement two sequence-to-sequence neural variational models - variational autoencoders (VAE) and variationa…

Text Generation

Improving VAEs' Robustness to Adversarial Attack

2019-06-01 · ICLR 2021 1 · Matthew Willetts, Alexander Camuto, Tom Rainforth, Stephen Roberts 외

Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to defend against such attacks remains an …

Adversarial Attack

A Bayesian Nonparametrics View into Deep Representations

2020-12-01 · NeurIPS 2020 12 · Michał Jamroż, Marcin Kurdziel, Mateusz Opala

We investigate neural network representations from a probabilistic perspective. Specifically, we leverage Bayesian nonparametrics to construct models of neural activations in Convolutional Neural Networks (CNNs) and late…

Memorization