arXiv 1605.061812016-05-20cs.LGcs.AIstat.ML

Variational hybridization and transformation for large inaccurate noisy-or networks

Baidu Research（百度研究院）

Yusheng Xie, Nan Du, Wei Fan, Jing Zhai, Weicheng Zhu

英文摘要：

Variational inference provides approximations to the computationally intractable posterior distribution in Bayesian networks. A prominent medical application of noisy-or Bayesian network is to infer potential diseases given observed symptoms. Previous studies focus on approximating a handful of complicated pathological cases using variational transformation. Our goal is to use variational transformation as part of a novel hybridized inference for serving reliable and real time diagnosis at web scale. We propose a hybridized inference that allows variational parameters to be estimated without disease posteriors or priors, making the inference faster and much of its computation recyclable. In addition, we propose a transformation ranking algorithm that is very stable to large variances in network prior probabilities, a common issue that arises in medical applications of Bayesian networks. In experiments, we perform comparative study on a large real life medical network and scalability study on a much larger (36,000x) synthesized network.

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

Robust Training of Graph Neural Networks via Noise Governance

Zhejiang University（浙江大学）；Alibaba Group（阿里巴巴集团）；Baidu Research（百度研究院）；University of Notre Dame（圣母大学）

Graph Neural Networks (GNNs) have become widely-used models for semi-supervised learning. However, the robustness of GNNs in the presence of label noise remains a largely under-explored problem. In this paper, we consider an important yet challenging scenario where labels on nodes of graphs are not only noisy but also scarce. In this scenario, the performance of GNNs is prone to degrade due to label noise propagation and insufficient learning. To address these issues, we propose a novel RTGNN (Robust Training of Graph Neural Networks via Noise Governance) framework that achieves better robustn…

2023-02-26cs.AIcs.LG

面向噪声标签学习的关系建模与蒸馏

Relation Modeling and Distillation for Learning with Noisy Labels

School of Mathematics and Computer, Shantou University（汕头大学数学与计算机学院）；School of Software, Shandong University（山东大学软件学院）；School of Chemistry and Life Sciences, Suzhou University of Science and Technology（苏州科技大学化学与生命科学学院）

针对模型对噪声标签过拟合的问题，提出即插即用的关系建模与蒸馏框架RMDNet，通过对比学习与知识蒸馏提取并校准表征，显著提升了模型在噪声数据上的泛化与判别性能。

2024-06-02cs.AI

Deep Gaussian Processes with Importance-Weighted Variational Inference

Imperial College London（帝国理工学院）

Deep Gaussian processes (DGPs) can model complex marginal densities as well as complex mappings. Non-Gaussian marginals are essential for modelling real-world data, and can be generated from the DGP by incorporating uncorrelated variables to the model. Previous work on DGP models has introduced noise additively and used variational inference with a combination of sparse Gaussian processes and mean-field Gaussians for the approximate posterior. Additive noise attenuates the signal, and the Gaussian form of variational distribution may lead to an inaccurate posterior. We instead incorporate nois…

2019-05-14cs.LGstat.ML

Non-Parametric Graph Learning for Bayesian Graph Neural Networks

McGill University（麦吉尔大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）

Graphs are ubiquitous in modelling relational structures. Recent endeavours in machine learning for graph-structured data have led to many architectures and learning algorithms. However, the graph used by these algorithms is often constructed based on inaccurate modelling assumptions and/or noisy data. As a result, it fails to represent the true relationships between nodes. A Bayesian framework which targets posterior inference of the graph by considering it as a random quantity can be beneficial. In this paper, we propose a novel non-parametric graph model for constructing the posterior distr…

2020-06-23cs.LGstat.ML

Joint Optimization Framework for Learning with Noisy Labels

The University of Tokyo（东京大学）

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and label…

2018-03-30cs.CVcs.LGstat.ML

噪声鲁棒对比学习用于动态系统中临界转变检测

Noise-robust Contrastive Learning for Critical Transition Detection in Dynamical Systems

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）

本文提出一种基于奇异值分解和半正交约束的轻量对比学习方法，用于提高动态系统中临界转变检测的鲁棒性与准确性。

2025-12-14cs.AIcs.LGphysics.comp-ph

更多相关论文收起更多论文

存在噪声处理且无辅助信息下的可辨识因果推断

Identifiable causal inference with noisy treatment and no side information

Aalto University（阿尔托大学）

针对处理变量有测量误差且无辅助信息的因果推断场景，提出基于深度潜变量模型的可辨识方法，无需已知测量误差方差即可得到可靠估计，拓展了因果推断的适用范围。

2024-09-12cs.LGstat.MEstat.ML

Gradient Profile Estimation Using Exponential Cubic Spline Smoothing in a Bayesian Framework

Attaining reliable profile gradients is of utmost relevance for many physical systems. In most situations, the estimation of gradient can be inaccurate due to noise. It is common practice to first estimate the underlying system and then compute the profile gradient by taking the subsequent analytic derivative. The underlying system is often estimated by fitting or smoothing the data using other techniques. Taking the subsequent analytic derivative of an estimated function can be ill-posed. The ill-posedness gets worse as the noise in the system increases. As a result, the uncertainty generated…

2019-12-09physics.data-anstat.ME

用于噪声标签学习的成对相似度分布聚类

Pairwise Similarity Distribution Clustering for Noisy Label Learning

本文提出 PSDC 样本选择算法，通过成对相似度与 GMM 建模将训练样本划分为干净集和噪声集，以增强半监督噪声标签学习，并在多个基准上显著优于现有方法。

2024-04-02cs.CVcs.LG

Adaptive Early-Learning Correction for Segmentation from Noisy Annotations

NYU Center for Data Science（纽约大学数据科学中心）；NYU Courant Institute of Mathematical Sciences（纽约大学库朗数学科学研究所）

Deep learning in the presence of noisy annotations has been studied extensively in classification, but much less in segmentation tasks. In this work, we study the learning dynamics of deep segmentation networks trained on inaccurately-annotated data. We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations. However, in contrast to classification, memorization in segmentation does not arise simultaneously for all sem…

2022-03-06cs.CVcs.LG

用于免疫组库分类与疾病相关免疫受体序列识别的噪声标签学习表述

A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification

Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）；National Genomics Data Center, Beijing Institute of Genomics, Chinese Academy of Sciences（中国科学院北京基因组研究所国家基因组科学数据中心）；China National Center for Bioinformation（国家生物信息中心）；College of Life Sciences, University of Chinese Academy of Sciences（中国科学院大学生命科学学院）

本文提出一种噪声标签学习框架解决免疫组库分类任务，通过非对称标签平滑、模型预测逐步修正及双模型协同训练策略，有效克服低见证率与确认偏差，在CMV和Cancer数据集上实现了高精度的序列级与组库级分类。

2023-07-29cs.LG

行走噪声：神经架构对噪声计算的分层鲁棒性及相关特征学习动态

Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics

Heidelberg University（海德堡大学）

本文提出 Walking Noise 方法，通过注入分层噪声研究神经网络分类器对加性、乘性及混合噪声的鲁棒性，发现带噪声训练可增大权重幅值或促使参数自二值化，从而提升信噪比和鲁棒性，并探讨其在噪声环境多重执行中的应用。

2024-06-14cs.ARcs.ETcs.LG

用于变分推断的稳健、精确随机优化

Robust, Accurate Stochastic Optimization for Variational Inference

本文针对变分推断中随机优化方法在高维和多样模型下不稳健的问题，提出将优化算法视为马尔可夫链的稳健随机优化框架，并配套收敛诊断与停止规则，可自动检测优化失败或不准确近似。

2020-09-03cs.LGstat.MEstat.ML

Epoch-wise label attacks for robustness against label noise

FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）

The current accessibility to large medical datasets for training convolutional neural networks is tremendously high. The associated dataset labels are always considered to be the real "ground truth". However, the labeling procedures often seem to be inaccurate and many wrong labels are integrated. This may have fatal consequences on the performance of both training and evaluation. In this paper, we show the impact of label noise in the training set on a specific medical problem based on chest X-ray images. With a simple one-class problem, the classification of tuberculosis, we measure the perf…

2019-12-12cs.CVcs.LG