首页/论文/2011.07137

arXiv 2011.071372020-11-13cs.LGcs.AI

On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision

Imperial College London（帝国理工学院）；University College London（伦敦大学学院）；City University of London（伦敦城市大学）

Harald Strömfelt, Luke Dickens, Artur d'Avila Garcez, Alessandra Russo

英文摘要：

We propose a new model for relational VAE semi-supervision capable of balancing disentanglement and low complexity modelling of relations with different symbolic properties. We compare the relative benefits of relation-decoder complexity and latent space structure on both inductive and transductive transfer learning. Our results depict a complex picture where enforcing structure on semi-supervised representations can greatly improve zero-shot transductive transfer, but may be less favourable or even impact negatively the capacity for inductive transfer.

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

Relational VAE: A Continuous Latent Variable Model for Graph Structured Data

ETH Zurich（苏黎世联邦理工学院）

Graph Networks (GNs) enable the fusion of prior knowledge and relational reasoning with flexible function approximations. In this work, a general GN-based model is proposed which takes full advantage of the relational modeling capabilities of GNs and extends these to probabilistic modeling with Variational Bayes (VB). To that end, we combine complementary pre-existing approaches on VB for graph data and propose an approach that relies on graph-structured latent and conditioning variables. It is demonstrated that Neural Processes can also be viewed through the lens of the proposed model. We sho…

2021-06-30cs.CEcs.LGstat.ML

具有因子分析潜空间的多模态层次变分自编码器

Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space

Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Instituto de Investigación Sanitaria Gregorio Marañón（格雷戈里奥·马拉尼翁健康研究所）

本文提出FA-VAE方法，将多个变分自编码器与因子分析潜空间结合，通过层次化的私有与共享潜空间设计，实现异构多视图数据的可解释、灵活、模块化建模，并支持跨域数据生成与迁移学习。

2024-10-22cs.AIcs.LG

RGCVAE：用于分子设计的关系图条件化变分自编码器

RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design

University of Padua（帕多瓦大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）

本文提出 RGCVAE，通过关系图同构编码器和新型概率解码器提升分子生成效果，在两个常用数据集上达到最先进性能并显著加快训练。

2023-06-08cs.AIcs.LGq-bio.BM

针对基于潜在扩散模型的图像编辑的灰盒攻击

A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse

School of Computer Science, University of St Andrews（圣安德鲁大学计算机科学学院）；Department of Data Science, City University of Hong Kong（香港城市大学数据科学系）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）；Department of Data Science and Artificial Intelligence, Monash University（墨尔本大学数据科学与人工智能系）；College of Information Science & Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）

本文提出了一种基于后验崩溃现象的灰盒攻击方法，通过调整参数实现两种崩溃类型，有效防止未经授权的图像编辑，且对模型依赖低，计算效率高。

2025-11-26cs.AIcs.CVcs.LG

Variational Relational Point Completion Network

Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic partial-to-complete mapping, but overlook structural relations in man-made objects. To tackle these challenges, this paper proposes a variational framework, Variational Relational point Completion network (VRCNet) with two appealing properties: 1) Probabilistic Modeling. In particular, we propose a dual-path architecture to enable principled probabi…

2021-04-20cs.CVcs.LG

用于鲁棒三维分类的变分关系点云补全网络

Variational Relational Point Completion Network for Robust 3D Classification

Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Lab（上海人工智能实验室）

本文提出变分关系点云补全网络VRCNet，通过双路径概率建模与点自注意力、选择性核模块增强局部细节，并构建MVP系列数据集，在补全基准和真实扫描上取得领先性能，显著提升部分点云的三维分类准确率。

2023-04-18cs.CVcs.LG

更多相关论文收起更多论文

SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations

Rutgers University - New Brunswick（罗格斯大学新布朗斯维克分校）；Rutgers University（罗格斯大学）

Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations. The ability to capture relations within data can provide the much needed inductive bias necessary for building more robust Machine Learning algorithms with more interpretable results. In this paper, inspired by recent advances in relational learning using Graph Neural Networks, we propose the Self-Attention Graph Variational AutoEncoder (SAG-VAE) network which can simultaneously learn feature relations and data representation…

2020-07-22cs.LGstat.ML

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression

Sun Yat-sen University（中山大学）；Alibaba Group（阿里巴巴集团）

On many natural language processing tasks, large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. Nevertheless, their huge model size and low inference speed have hindered the deployment on resource-limited devices in practice. In this paper, we target to compress PLMs with knowledge distillation, and propose a hierarchical relational knowledge distillation (HRKD) method to capture both hierarchical and domain relational information. Specifically, to enhance the model capability and transferability, we leverage the idea o…

2021-10-16cs.AIcs.CLcs.LG

基于位置感知图增强变分自编码器的网络化时间序列插补

Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research（IBM研究院）

针对网络化时间序列（NTS）中图结构动态变化且存在缺失值的问题，提出PoGeVon模型，利用变分自编码器（VAE）结合基于带重启随机游走（RWR）的节点位置嵌入，通过多任务学习的3阶段解码器相互插补时间序列与图结构缺失值，实现了比基线更优的插补效果。

2023-06-26cs.AIcs.LG

SCGFM-ART：面向结构中心图基础模型的摊销关系传输

SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Models

University of Electronic Science and Technology of China（电子科技大学）

提出SCGFM-ART框架，通过摊销关系传输将任意图对齐到共享关系图谱，实现跨域图表示学习，在14个任务上取得最优迁移性能，并大幅加速推理。

2026-09-18cs.AIcs.LG

Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoders

Max Planck Institute for Polymer Research（马克斯·普朗克聚合物研究所）；Koc University（科奇大学）

Extracting insight from the enormous quantity of data generated from molecular simulations requires the identification of a small number of collective variables whose corresponding low-dimensional free-energy landscape retains the essential features of the underlying system. Data-driven techniques provide a systematic route to constructing this landscape, without the need for extensive a priori intuition into the relevant driving forces. In particular, autoencoders are powerful tools for dimensionality reduction, as they naturally force an information bottleneck and, thereby, a low-dimensional…

2019-12-22cs.LGphysics.chem-phstat.ML

边缘精度不够：为何动力学学习到的结构无法迁移到反问题

Edge Accuracy Is Not Enough: Why Dynamics-Learned Structure Fails to Transfer to Inverse Problems

Institute for Data Processing and Electronics (IPE)（数据处理与电子研究所）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）

该论文证明，从动力学预测中学习到的结构即使满足理论条件，在反问题迁移中仍会失败，并提出了基于Jaccard相似度的轻量级可迁移性测试来预测迁移成败。

2026-10-08cs.LG