检索结果-内蒙古大学图书馆

Uncertainty-Aware Heterogeneous Representation Learning in POI Recommender Systems

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2023年第7期53卷 4522-4535页

作者： Zhou, Fan Qian, Tangjiang Mo, Yuhua Cheng, Zhangtao Xiao, Chunjing Wu, Jin Trajcevski, Goce Univ Elect Sci & Technol China Chengdu 610054 Peoples R China Henan Univ Henan Key Lab Big Data Anal & Proc Kaifeng 475004 Peoples R China Iowa State Univ Dept Elect & Comp Engn Ames IA 50011 USA

Discovering interesting yet unvisited point-of-interests (POIs) is among the most practical applications but challenging problems in location-based social networks (LBSNs). Popular approaches face several issues, such as data sparsity and difficulties in modeling latent nonlinearity between users and POIs. Furthermore, the uncertainty in LBSNs poses additional obstacles to learning good representations of users' general and current interests. To effectively address these issues, we postulate that fusing multiple sources of information is paramount. Toward that, we propose a novel deep generative recommender system-wasserstein autoencoder for POI recommendation (WaPOIR). It unifies the information from users' personal preference, social influence, and geographical data, and captures users' general interests from historical check-ins, while modeling users' current interests from recently visited POIs. Unlike previous methods, WaPOIR learns the latent distribution of data in the wasserstein space as a potential representation for each POI and each user in LBSNs. This enables simultaneous maintenance of social and POI interactions and modeling the uncertainty of their relationships. WaPOIR is a stochastic recommendation approach that allows Bayesian inference and approximation of variational posterior distribution. Extensive experiments conducted on real-world LBSN datasets demonstrate that WaPOIR achieves better performance over the state-of-the-art approaches.

关键词： Data models Uncertainty Stochastic processes Social networking (online) Gaussian distribution Bayes methods Recommender systems Adversarial learning collaborative filtering (CF) point-of-interest (POI) recommendation variational inference wasserstein autoencoder

来源：评论

学校读者我要写书评

暂无评论

Euler-Lagrange Analysis of Generative Adversarial Networks

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2023年第1期24卷 1-100页

作者： Asokan, Siddarth Seelamantula, Chandra Sekhar Indian Inst Sci Robert Bosch Ctr Cyber Bengaluru 560012 India Indian Inst Sci Dept Elect Engn Bengaluru 560012 India

We consider Generative Adversarial Networks (GANs) and address the underlying functional optimization problem ab initio within a variational setting. Strictly speaking, the optimization of the generator and discriminator functions must be carried out in accordance with the Euler-Lagrange conditions, which become particularly relevant in scenarios where the optimization cost involves regularizers comprising the derivatives of these functions. Considering wasserstein GANs (WGAN) with a gradient-norm penalty, we show that the optimal discriminator is the solution to a Poisson differential equation. In principle, the optimal discriminator can be obtained in closed form without having to train a neural network. We illustrate this by employing a Fourier-series approximation to solve the Poisson differential equation. Experimental results based on synthesized Gaussian data demonstrate superior convergence behavior of the proposed approach in comparison with the baseline WGAN variants that employ weight-clipping, gradient or Lipschitz penalties on the discriminator on low-dimensional data. We also analyze the truncation error of the Fourier-series approximation and the estimation error of the Fourier coefficients in a high-dimensional setting. We demonstrate applications to real-world images considering latent-space prior matching in wasserstein autoencoders and present performance comparisons on benchmark datasets such as MNIST, SVHN, CelebA, CIFAR-10, and Ukiyo-E. We demonstrate that the proposed approach achieves comparable reconstruction error and Fre ' chet inception distance with faster convergence and up to two-fold improvement in image sharpness.

关键词： Generative adversarial networks Calculus of variations Euler-Lagrange conditions Fourier-series approximation wasserstein autoencoder

来源：评论

学校读者我要写书评

暂无评论

DISCRETE wasserstein autoencoderS FOR DOCUMENT RETRIEVAL

DISCRETE WASSERSTEIN AUTOENCODERS FOR DOCUMENT RETRIEVAL

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhang, Yifei Zhu, Hao Alibaba Grp Hangzhou Zhejiang Peoples R China Australian Natl Univ Canberra ACT Australia

ISBN: (纸本)9781509066315

Learning to hash via generative models has became a promising paradigm for fast similarity search in document retrieval. The binary hash codes are treated as Bernoulli latent variables when training a variational autoencoder (VAE). However, the prior of discrete distribution (i.e., Bernoulli distribution) is short of some structure regularization to generate more efficient binary codes. In this paper, we present an end-to-end wasserstein autoencoder (WAE) for text hashing to avoid in-differentiable operators in the reparameterization trick, where the latent variables can be imposed to any discrete priors we can sample by using adversarial learning. Moreover, we can generate more efficient discrete codes by imposing a structural constraint on priors like the bit balance constraint. Our experiments show that the proposed model is competitive to the state of the art methods on both unsupervised and supervised scenarios.

关键词： wasserstein autoencoder Documental Retrieval Learning to Hash

来源：评论

学校读者我要写书评

暂无评论

Towards a configurable and non-hierarchical search space for NAS

引用

NEURAL NETWORKS 2024年 180卷 106700页

作者： Perrin, Mathieu Guicquero, William Paille, Bruno Sicard, Gilles ST Microelect 12 Rue Jules Horowitz F-38019 Grenoble France Univ Grenoble Alpes CEA LETI 17 Ave Martyrs F-38000 Grenoble France

Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most. To improve flexibility, and be less reliant on expert knowledge, this paper proposes a NAS methodology in which the search space is easily customizable, and allows for full network search. NAS is performed with Gaussian Process (GP)-based Bayesian Optimization (BO) in a continuous architecture embedding space. This embedding is built upon a wasserstein autoencoder, regularized by both a Maximum Mean Discrepancy (MMD) penalization and a Fully Input Convex Neural Network (FICNN) latent predictor, trained to infer the parameter count of architectures. This paper first assesses the embedding's suitability for optimization by solving 2 computationally inexpensive problems: minimizing the number of parameters, and maximizing a zero-shot accuracy proxy. Then, two variants of complexity-aware NAS are performed on CIFAR-10 and STL-10, based on two different search spaces, providing competitive NN architectures with limited model sizes.

关键词： Neural architecture search Convolutional neural network wasserstein autoencoder Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Preserving Data Manifold Structure in Latent Space for Exploration through Network Geodesics

Preserving Data Manifold Structure in Latent Space for Explo...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Krishnagopal, Sanjukta Bedrossian, Jacob UCL Gatsby Computat Neurosci Unit London W1T 4JG England Univ Maryland Dept Math College Pk MD 20742 USA

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

While variational autoencoders have been successful in several tasks, the use of conventional priors are limited in their ability to encode the underlying structure of input data. We introduce an Encoded Prior Sliced wasserstein autoencoder wherein an additional prior-encoder network learns a geometry and topology preserving embedding of any data manifold, thus improving the structure of latent space. The autoencoder and prior-encoder networks are iteratively trained using the Sliced wasserstein distance, which facilitates the learning of nonstandard complex priors. We then introduce a graph-based algorithm to explore the learned manifold by traversing latent space through network-geodesics that lie along the manifold and hence are more realistic compared to conventional Euclidean interpolation. Specifically, we identify network-geodesics by maximizing the density of samples along the path while minimizing total energy. We use the 3D-spiral data to show that the prior encodes the geometry underlying the data unlike conventional autoencoders, and to demonstrate the exploration of the embedded data manifold through the network algorithm. We apply our framework to artificial as well as image datasets to demonstrate the advantages of learning improved latent structure, outlier generation, and geodesic interpolation.

关键词： data manifold wasserstein autoencoder data embedding representation learning latent representation network geodesics

来源：评论

学校读者我要写书评

暂无评论

A lightweight propagation path aggregating network with neural topic model for rumor detection

引用

NEUROCOMPUTING 2021年 458卷 468-477页

作者： Zhang, Pengfei Ran, Hongyan Jia, Caiyan Li, Xuanya Han, Xueming Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Key Lab Traff Data Anal & Min Beijing 100044 Peoples R China Baidu Inc Beijing Peoples R China

The structure information associated with message propagation has been proved to be effective to distinguish false and true rumors. However, existing methods lack an efficient way to learn the representation of the whole rumors which captures the intrinsic mechanism of rumor propagation structures and semantics. In this study, we propose a lightweight propagation path aggregating (PPA) neural network for rumor embedding and classification. In the network, we first model the propagation structure of each rumor as an independent set of propagation paths in which each path represents the source post in a different talking context. We then aggregate all paths to obtain the representation of the whole propagation structure. Besides, we utilize a neural topic model in the wasserstein autoencoder (WAE) framework to capture event insensitive stance patterns in response propagation trees where no source post is included. Empirical studies demonstrate that 1) PPA achieves the state-of-the-art performance with much less parameters and training time, 2) PPA can further benefit from the pre-trained neural topic model which enables to fully use unlabeled data, thus improves the performance of PPA especially when labeled samples are limited or rumors are spreading at early stage. Meanwhile, this topic model offers an explicit interpretation of stance patterns in the form of topics, consequently improves interpretability of the PPA network. The source code can be available at https://***/zperfet/PathFakeGit. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Rumor detection wasserstein autoencoder Neural topic model Propagation structure Lightweight

来源：评论

学校读者我要写书评

暂无评论

Euler-Lagrange analysis of generative adversarial networks

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 5709-5808页

作者： Siddarth Asokan Chandra Sekhar Seelamantula Robert Bosch Centre for Cyber-Physical Systems Indian Institute of Science Bengaluru India Department of Electrical Engineering Indian Institute of Science Bengaluru India

We consider Generative Adversarial Networks (GANs) and address the underlying functional optimization problem ab initio within a variational setting. Strictly speaking, the optimization of the generator and discriminator functions must be carried out in accordance with the Euler-Lagrange conditions, which become particularly relevant in scenarios where the optimization cost involves regularizers comprising the derivatives of these functions. Considering wasserstein GANs (WGAN) with a gradient-norm penalty, we show that the optimal discriminator is the solution to a Poisson differential equation. In principle, the optimal discriminator can be obtained in closed form without having to train a neural network. We illustrate this by employing a Fourier-series approximation to solve the Poisson differential equation. Experimental results based on synthesized Gaussian data demonstrate superior convergence behavior of the proposed approach in comparison with the baseline WGAN variants that employ weight-clipping, gradient or Lipschitz penalties on the discriminator on low-dimensional data. We also analyze the truncation error of the Fourier-series approximation and the estimation error of the Fourier coefficients in a high-dimensional setting. We demonstrate applications to real-world images considering latent-space prior matching in wasserstein autoencoders and present performance comparisons on benchmark datasets such as MNIST, SVHN, CelebA, CIFAR-10, and Ukiyo-E. We demonstrate that the proposed approach achieves comparable reconstruction error and Fréchet inception distance with faster convergence and up to two-fold improvement in image sharpness.

关键词： generative adversarial networks calculus of variations Euler-Lagrange conditions Fourier-series approximation wasserstein autoencoder

来源：评论

学校读者我要写书评

暂无评论

Improving Gaussian mixture latent variable model convergence with Optimal Transport 13

Improving Gaussian mixture latent variable model convergence...

引用

13th Asian Conference on Machine Learning (ACML)

作者： Gaujac, Benoit Feige, Ilya Barber, David UCL London England

Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets. They present, however, subtleties in training often manifesting in the discrete latent variable not being leveraged. In this paper, we show why such models struggle to train using traditional log-likelihood maximization, and that they are amenable to training using the Optimal Transport framework of wasserstein autoencoders. We find our discrete latent variable to be fully leveraged by the model when trained, without any modifications to the objective function or significant fine tuning. Our model generates comparable samples to other approaches while using relatively simple neural networks, since the discrete latent variable carries much of the descriptive burden. Furthermore, the discrete latent provides significant control over generation.

关键词： Optimal Transport wasserstein autoencoder Variational autoencoder Latent variable modeling Generative modeling

来源：评论

学校读者我要写书评

暂无评论

Regularized siamese neural network for unsupervised outlier detection on brain multiparametric magnetic resonance imaging: Application to epilepsy lesion screening

引用

MEDICAL IMAGE ANALYSIS 2020年第0期60卷 101618-000页

作者： Alaverdyan, Zaruhi Jung, Julien Bouet, Romain Lartizien, Carole Univ Claude Bernard Lyon 1 Univ Lyon INSA Lyon UJM St EtienneINSERMCREATISUMR 5220U1206CNRS F-69621 Lyon France Univ Lyon 1 CNRS INSERM U1028 Lyon Neurosci Res CtrCRNLUMR5292 Lyon France

In this study, we propose a novel anomaly detection model targeting subtle brain lesions in multiparametric MRI. To compensate for the lack of annotated data adequately sampling the heterogeneity of such pathologies, we cast this problem as an outlier detection problem and introduce a novel configuration of unsupervised deep siamese networks to learn normal brain representations using a series of non-pathological brain scans. The proposed siamese network, composed of stacked convolutional autoencoders as subnetworks is designed to map patches extracted from healthy control scans only and centered at the same spatial localization to 'close' representations with respect to the chosen metric in a latent space. It is based on a novel loss function combining a similarity term and a regularization term compensating for the lack of dissimilar pairs. These latent representations are then fed into oc-SVM models at voxel-level to produce anomaly score maps. We evaluate the performance of our brain anomaly detection model to detect subtle epilepsy lesions in multiparametric (T1-weighted, FLAIR) MRI exams considered as normal (MRI-negative). Our detection model trained on 75 healthy subjects and validated on 21 epilepsy patients (with 18 MRI-negatives) achieves a maximum sensitivity of 61% on the MRI-negative lesions, identified among the 5 most suspicious detections on average. It is shown to outperform detection models based on the same architecture but with stacked convolutional or wasserstein autoencoders as unsupervised feature extraction mechanisms. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Regularized siamese network wasserstein autoencoder Unsupervised representation learning Brain lesions Anomaly detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：