paper-with-me

Papers

Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs

2025-02-16 · Xin Gao, Jian Pu

Multi-View Representation Learning (MVRL) aims to derive a unified representation from multi-view data by leveraging shared and complementary information across views. However, when views are irregularly missing, the incomplete data can lead to representations that lack sufficiency and consistency. To address this, we propose Multi-View Permutation of Variational Auto-Encoders (MVP), which excavates invariant relationships between views in incomplete data. MVP establishes inter-view correspondences in the latent space of Variational Auto-Encoders, enabling the inference of missing views and the aggregation of more sufficient information. To derive a valid Evidence Lower Bound (ELBO) for learning, we apply permutations to randomly reorder variables for cross-view generation and then partition them by views to maintain invariant meanings under permutations. Additionally, we enhance consistency by introducing an informational prior with cyclic permutations of posteriors, which turns the regularization term into a similarity measure across distributions. We demonstrate the effectiveness of our approach on seven diverse datasets with varying missing ratios, achieving superior performance in multi-view clustering and generation tasks.

📄 PDF Abstract BibTeX arXiv:2502.11037

Code (0)

등록된 구현이 없습니다.

Tasks

MULTI-VIEW LEARNINGRepresentation Learningvalid

Similar Papers 제목 키워드 기반

Handling Incomplete Heterogeneous Data using VAEs

2018-07-10 · Alfredo Nazabal, Pablo M. Olmos, Zoubin Ghahramani, Isabel Valera

Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAE…

Imputation

On sparsity, extremal structure, and monotonicity properties of Wasserstein and Gromov-Wasserstein optimal transport plans

2026-02-18 · Titouan Vayer arxiv

This note gives a self-contained overview of some important properties of the Gromov-Wasserstein (GW) distance, compared with the standard linear optimal transport (OT) framework. More specifically, I explore the followi…

CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning

2026-02-04 · Ronghao Lin, Qiaolin He, Sijie Mai, Ying Zeng 외 arxiv

Multimodal machine learning, mimicking the human brain's ability to integrate various modalities has seen rapid growth. Most previous multimodal models are trained on perfectly paired multimodal input to reach optimal pe…

MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training

2022-02-08 · Ertuğ Karamatlı, Serap Kırbız

We introduce two unsupervised source separation methods, which involve self-supervised training from single-channel two-source speech mixtures. Our first method, mixture permutation invariant training (MixPIT), enables l…

Data AugmentationSpeech Separation

Correlated Variational Auto-Encoders

2019-05-14 · ICLR Workshop DeepGenStruct 2019 · Da Tang, Dawen Liang, Tony Jebara, Nicholas Ruozzi

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to acc…

ClusteringLink Prediction