English
Related papers

Related papers: A Multi-Level Causal Intervention Framework for Me…

200 papers

Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables. In this paper, we investigate several multi-level structures to learn a VAE model to generate…

Computation and Language · Computer Science 2019-06-21 Dinghan Shen , Asli Celikyilmaz , Yizhe Zhang , Liqun Chen , Xin Wang , Jianfeng Gao , Lawrence Carin

Concept-based eXplainable AI (C-XAI) is a rapidly growing research field that enhances AI model interpretability by leveraging intermediate, human-understandable concepts. This approach not only enhances model transparency but also enables…

Machine Learning · Computer Science 2025-04-08 Francesco De Santis , Gabriele Ciravegna , Philippe Bich , Danilo Giordano , Tania Cerquitelli

Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We…

Machine Learning · Computer Science 2020-05-29 Andriy Serdega , Dae-Shik Kim

Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…

Machine Learning · Computer Science 2022-03-30 Trung Ngo , Najwa Laabid , Ville Hautamäki , Merja Heinäniemi

After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an…

Machine Learning · Computer Science 2019-07-08 Sangchul Hahn , Heeyoul Choi

The interpretability of generative models is considered a key factor in demonstrating their effectiveness and controllability. The generated data are believed to be determined by latent variables that are not directly observable. Therefore,…

Machine Learning · Statistics 2025-08-14 Yuan-Hao Wei , Fu-Hao Deng , Lin-Yong Cui , Yan-Jie Sun

Current state-of-the-art generative approaches frequently rely on a two-stage training procedure, where an autoencoder (often a VAE) first performs dimensionality reduction, followed by training a generative model on the learned latent…

Machine Learning · Statistics 2025-07-15 Gianluigi Silvestri , Luca Ambrogioni

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Simone Foti , Bongjin Koo , Danail Stoyanov , Matthew J. Clarkson

Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction.…

Machine Learning · Statistics 2022-06-10 Kenneth Ezukwoke , Anis Hoayek , Mireille Batton-Hubert , Xavier Boucher

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample efficiency for…

Machine Learning · Computer Science 2021-10-26 Junwen Bai , Weiran Wang , Carla Gomes

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

Sound · Computer Science 2020-07-29 Siddique Latif , Rajib Rana , Junaid Qadir , Julien Epps

Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition drives optimization…

Machine Learning · Computer Science 2026-05-18 Hazhir Aliahmadi , Irina Babayan , Greg van Anders

Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are…

Machine Learning · Computer Science 2025-02-14 Angus Nicolson , Lisa Schut , J. Alison Noble , Yarin Gal

This work presents an analysis of the hidden representations of Variational Autoencoders (VAEs) using the Intrinsic Dimension (ID) and the Information Imbalance (II). We show that VAEs undergo a transition in behaviour once the bottleneck…

Machine Learning · Computer Science 2024-11-05 Charles Camboulin , Diego Doimo , Aldo Glielmo

Generative AI models for music and the arts in general are increasingly complex and hard to understand. The field of eXplainable AI (XAI) seeks to make complex and opaque AI models such as neural networks more understandable to people. One…

Sound · Computer Science 2024-02-06 Nick Bryan-Kinns , Bingyuan Zhang , Songyan Zhao , Berker Banar

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-dimensional latent…

Machine Learning · Statistics 2021-03-03 Marissa C. Connor , Gregory H. Canal , Christopher J. Rozell

In disentangled representation learning, the goal is to achieve a compact representation that consists of all interpretable generative factors in the observational data. Learning disentangled representations for graphs becomes increasingly…

Machine Learning · Computer Science 2023-11-20 Jingyun Feng , Lin Zhang , Lili Yang

Variational autoencoders are prominent generative models for modeling discrete data. However, with flexible decoders, they tend to ignore the latent codes. In this paper, we study a VAE model with a deterministic decoder (DD-VAE) for…

Machine Learning · Computer Science 2020-03-05 Daniil Polykovskiy , Dmitry Vetrov

Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. We develop three variations on VAEs by introducing a second parameterized encoder/decoder pair and,…

Machine Learning · Computer Science 2023-04-06 R. I. Cukier