arXiv 2202.041782022-02cs.PLcs.LG

VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming

University of Bologna（博洛尼亚大学）；KU Leuven（鲁汶大学）

Eleonora Misino, Giuseppe Marra, Emanuele Sansone

英文摘要：

We present VAEL, a neuro-symbolic generative model integrating variational autoencoders (VAE) with the reasoning capabilities of probabilistic logic (L) programming. Besides standard latent subsymbolic variables, our model exploits a probabilistic logic program to define a further structured representation, which is used for logical reasoning. The entire process is end-to-end differentiable. Once trained, VAEL can solve new unseen generation tasks by (i) leveraging the previously acquired knowledge encoded in the neural component and (ii) exploiting new logical programs on the structured latent space. Our experiments provide support on the benefits of this neuro-symbolic integration both in terms of task generalization and data efficiency. To the best of our knowledge, this work is the first to propose a general-purpose end-to-end framework integrating probabilistic logic programming into a deep generative model.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Variational Autoencoder with Learned Latent Structure

Georgia Institute of Technology（佐治亚理工学院）

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 vectors to high-dimensional data while encouraging a global structure in the latent space through the use of a specified prior distribution. When this prior does not match the structure of the true data manifold, it can lead to a less accurate model of the data. To resolve this mismatch, we introduce the Variational Autoencoder with Learned Latent Structure (…

2021-03-02cs.LGstat.ML

弥合多模态变分自编码器中的推断差距

Bridging the inference gap in Mutimodal Variational Autoencoders

Inria Paris（法国国家信息与自动化研究所巴黎分部）；Inserm（法国国家健康与医学研究院）

本文提出一种无需专家混合聚合的多模态变分自编码器，通过多阶段训练结合变分推断与归一化流，并利用模态间共享信息提升条件生成质量，在多个基准上达到最优性能。

2025-02-06cs.LGstat.ML

Bridging the ELBO and MMD

University College London（伦敦大学学院）

One of the challenges in training generative models such as the variational auto encoder (VAE) is avoiding posterior collapse. When the generator has too much capacity, it is prone to ignoring latent code. This problem is exacerbated when the dataset is small, and the latent dimension is high. The root of the problem is the ELBO objective, specifically the Kullback-Leibler (KL) divergence term in objective function \citep{zhao2019infovae}. This paper proposes a new objective function to replace the KL term with one that emulates the maximum mean discrepancy (MMD) objective. It also introduces …

2019-10-29cs.LGstat.ML

Towards Visually Explaining Variational Autoencoders

Rensselaer Polytechnic Institute（伦斯勒理工学院）；United Imaging Intelligence（联影智能）；University of California Riverside（加州大学河滨分校）；Northeastern University（东北大学）

Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent effort in using visual attention maps as a means for visual explanations. A key problem, however, is these methods are designed for classification and categorization tasks, and their extension to explaining generative models, e.g. variational autoencoders (VAE) is not trivial. In this work, we take a step towards bridging this crucial gap, proposing the firs…

2020-04-14cs.CVcs.LG

变分推断、自编码器与扩散模型的频率派统计学导论

A Frequentist Statistical Introduction to Variational Inference, Autoencoders, and Diffusion Models

Yen-Chi Chen（独立研究者）

本文从频率派统计学视角出发，以经典EM算法为基础阐释变分推断、变分自编码器和去噪扩散模型的理论，弥合经典统计推断与现代生成式AI间的学科认知壁垒。

2025-10-21cs.LGstat.COstat.ME

Phase-Type变分自编码器用于重尾数据

Phase-Type Variational Autoencoders for Heavy-Tailed Data

Université Paris Saclay, Lab. MICS, CentraleSupélec, Gif-sur-Yvette, France（巴黎萨克雷大学，MICS实验室，CentraleSupélec，法国吉夫-sur-依夫）

提出Phase-Type变分自编码器（PH-VAE），通过将解码器分布建模为潜在条件相位型分布（连续时间马尔可夫链的吸收时间），灵活适应重尾行为，在合成和真实基准上优于高斯、Student-t和极值VAE解码器。

2026-05-26cs.AIcs.LGstat.ML

更多相关论文收起更多论文

Latent Translation: Crossing Modalities by Bridging Generative Models

Stony Brook University（石溪大学）；Google AI（谷歌人工智能）

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc interface between two existing models to solve a new task. Specifically, we take inspiration from neural machine translation, and cast the challenging problem of cross-modal domain transfer as unsupervised translation between the latent spaces of pretrained deep generative models. By abstracting away the data representation, we demonstrate that it is possible …

2019-02-21cs.LGcs.NEstat.ML

桥接语言、视觉与动作：机器人操作任务中的多模态 VAE

Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks

Czech Institute of Informatics, Robotics and Cybernetics（捷克信息学、机器人学与自动控制研究所）；Czech Technical University in Prague（布拉格捷克技术大学）

本文研究机器人操作中的无监督视觉-语言-动作映射，提出轻量级多模态 VAEs 方法，并引入模型无关训练方案将模拟器性能提升达 55%，系统评估了任务变量挑战及 VAEs 的应用潜力与局限。

2025-05-28cs.LGcs.RO

通过VAE-EM估计弥合电子显微镜校准的仿真到现实差距

Bridging the Simulation-to-Reality Gap in Electron Microscope Calibration via VAE-EM Estimation

Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology（控制系统技术部，机械工程系，埃因霍温理工大学）

本文提出利用VAE-EM方法解决扫描透射电子显微镜的校准问题，通过学习低维图像表示和联合估计模型参数，实现更快速和一致的校准结果。

2026-03-19cs.CVcs.LG

MMbeddings：受非线性混合模型启发的参数高效、低过拟合概率嵌入

MMbeddings: Parameter-Efficient, Low-Overfitting Probabilistic Embeddings Inspired by Nonlinear Mixed Models

本文提出概率嵌入方法MMbeddings，通过非线性混合模型视角在变分自编码器框架内将嵌入视为潜在随机效应，大幅减少与基数无关的参数量，有效缓解高基数场景下的过拟合与计算负担，并在多种任务中优于传统嵌入。

2025-11-01cs.LGstat.ML

A Variational Perspective on Diffusion-Based Generative Models and Score Matching

University of Montreal（蒙特利尔大学）；Mila（米拉）

Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image data. Recently, Song et al. (2021) show that diffusion processes that transform data into noise can be reversed via learning the score function, i.e. the gradient of the log-density of the perturbed data. They propose to plug the learned score function into an inverse formula to define a generative diffusion process. Despite the empirical success, a theoretical underpinning of this procedure is still lacking. In this work, we approach the (continuous-time) …

2021-09-30cs.LG

用于高维项目因子分析的生成对抗网络：一种深度对抗学习算法

Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm

University of Toronto（多伦多大学）

针对传统VAEs在高维项目因子分析（IFA）中表达能力受限的问题，提出结合GANs优势的AVB及增强算法IWAVB，通过对抗博弈提升参数估计的灵活性与准确性，实验证明其在似然和多峰分布处理上优于IWAE，并有望推动心理测量与多模态数据整合。

2025-10-31cs.LGstat.APstat.CO

量子生成模型用于计算流体力学：对格子玻尔兹曼模拟中潜在空间学习的首次探索

Quantum Generative Models for Computational Fluid Dynamics: A First Exploration of Latent Space Learning in Lattice Boltzmann Simulations

Al Akhawayn University（阿尔阿赫韦因大学）

本文首次将量子生成模型应用于CFD数据的潜在空间学习，通过对比量子与经典方法，展示了在格子玻尔兹曼模拟中提升生成样本质量的潜力。

2025-12-27cs.LG

基于VAE的方法采样多变量极值

A VAE Approach to Sample Multivariate Extremes

Laboratoire des Sciences du Climat et de l’Environnement ESTIMR, CNRS-CEA-UVSQ（气候与环境科学实验室 ESTIMR，法国国家科学研究中心-法国原子能委员会-巴黎-萨克雷大学）；IMT Atlantique, Lab-STICC ODISSEY, INRIA（IMT大西洋，Lab-STICC ODISSEY，法国国家信息与自动化技术研究所）

本文提出了一种基于VAE的方法，用于采样多变量厚尾分布，以提高极值之间依赖结构的学习，并应用于洪水风险评估。

2026-01-30cs.LGstat.ML

CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning

Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）

It is known that the inconsistent distribution and representation of different modalities, such as image and text, cause the heterogeneity gap that makes it challenging to correlate such heterogeneous data. Generative adversarial networks (GANs) have shown its strong ability of modeling data distribution and learning discriminative representation, existing GANs-based works mainly focus on generative problem to generate new data. We have different goal, aim to correlate heterogeneous data, by utilizing the power of GANs to model cross-modal joint distribution. Thus, we propose Cross-modal GANs …

2018-04-26cs.CVcs.LGcs.MM