paper-with-me

Papers

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

2020-06-21 · NeurIPS 2020 12 · Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato, Richard Turner, Cheng Zhang

Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of features (categorical, ordinal, continuous, etc.) and features of the same type having different marginal distributions. We propose an extension of variational autoencoders (VAEs) called VAEM to handle such heterogeneous data. VAEM is a deep generative model that is trained in a two stage manner such that the first stage provides a more uniform representation of the data to the second stage, thereby sidestepping the problems caused by heterogeneous data. We provide extensions of VAEM to handle partially observed data, and demonstrate its performance in data generation, missing data prediction and sequential feature selection tasks. Our results show that VAEM broadens the range of real-world applications where deep generative models can be successfully deployed.

📄 PDF Abstract BibTeX arXiv:2006.11941

Code (2)

microsoft/VAEM 공식 구현 tf
ipeis/HH-VAEM pytorch

Tasks

feature selectionVocal Bursts Type Prediction

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

2022-02-09 · Ignacio Peis, Chao Ma, José Miguel Hernández-Lobato

Variational Autoencoders (VAEs) have recently been highly successful at imputing and acquiring heterogeneous missing data. However, within this specific application domain, existing VAE methods are restricted by using on…

Active LearningImputation

Corn Yield Prediction based on Remotely Sensed Variables Using Variational Autoencoder and Multiple Instance Regression

2022-11-23 · Zeyu Cao, Yuchi Ma, Zhou Zhang

In the U.S., corn is the most produced crop and has been an essential part of the American diet. To meet the demand for supply chain management and regional food security, accurate and timely large-scale corn yield predi…

Anomaly DetectionCrop Yield PredictionManagementPrediction+1

CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generation

2025-06-17 · Jia-Chen Zhang, Zheng Zhou, Yu-jie Xiong, Chun-Ming Xia 외

Training data has been proven to be one of the most critical components in training generative AI. However, obtaining high-quality data remains challenging, with data privacy issues presenting a significant hurdle. To ad…

Tabular Data Generation

VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

2025-05-05 · Hao Cheng, Zhiwei Zhao, Yichao He, Zhenzhen Hu 외

Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the in…

Contrastive LearningDynamic Facial Expression RecognitionEmotion RecognitionRepresentation Learning+2

Conditional-Independence-Regularized Distributional Autoencoders for Mixed-Type Data

2026-08-20 · Siyuan Tang, Gongjun Xu, Ji Zhu arxiv

Mixed-type data containing both numerical and categorical variables arise in many scientific and real-world applications. Existing representation learning and generative modeling approaches typically focus either on reco…

Representation Learning