检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Kuschel, Maurice Alkhatib, Amr Hasija, Tanuj Boström, Henrik Signal and System Theory Group Paderborn University Paderborn Germany Division of Software and Computer Systems KTH Royal Institue of Technology Stockholm Sweden

ISBN: (纸本)9798350368741

multiview representation learning techniques based on deep correlation maximization have become increasingly popular for learning meaningful and compact representations from multiview data. Even though their performance is state-of-the-art in many interpretability-critical fields, their black-box behavior poses a problem and restricts their usability. To overcome this restriction, we propose XDCCA (eXplanations for Deep Canonical Correlation Analysis), an explanation strategy using characteristic rules in combination with SHAP that exploits the inherent structure of latent spaces created by correlation maximization techniques. We demonstrate how XDCCA allows for interpreting learned representations and their correlation using real medical time series and synthetic image data. © 2025 IEEE.

关键词： CEGA Deep Canonical Correlation Analysis Explainable AI multiview representation learning SHAP

来源：评论

学校读者我要写书评

暂无评论

multiview representation learning via Deep CCA for Silent Speech Recognition 18

Multiview Representation Learning via Deep CCA for Silent Sp...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Kim, Myungjong Cao, Beiming Mau, Ted Wang, Jun Univ Texas Dallas Dept Bioengn Speech Disorders & Technol Lab Richardson TX 75083 USA Univ Texas Dallas Callier Ctr Commun Disorders Richardson TX 75083 USA Univ Texas Southwestern Med Ctr Dallas Dept Otolaryngol Head & Neck Surg Dallas TX 75390 USA

ISBN: (纸本)9781510848764

Silent speech recognition (SSR) converts non-audio information such as articulatory (tongue and lip) movements to text. Articulatory movements generally have less information than acoustic features for speech recognition, and therefore. the performance of SSR may be limited. multiview representation learning, which can learn better representations by analyzing multiple information sources simultaneously, has been recently successfully used in speech processing and acoustic speech recognition. However, it has rarely been used in SSR. In this paper, we investigate SSR based on multiview representation learning via canonical correlation analysis (CCA). When both acoustic and articulatory data are available during training, it is possible to effectively learn a representation of articulatory movements from the multiview data with CCA. To further represent the complex structure of the multiview data, we apply deep CCA, where the functional form of the feature mapping is a deep neural network. This approach was evaluated in a speaker-independent SSR task using a data set collected from seven English speakers using an electromagnetic articulograph (EMA). Experimental results showed the effectiveness of the multiview representation learning via deep CCA over the CCA-based multiview approach as well as baseline articulatory movement data on Gaussian mixture model and deep neural network-based SSR systems.

关键词： articulatory movements deep canonical correlation analysis multiview representation learning silent speech recognition

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks with Dependency Parser towards multiview representation learning for Sentiment Analysis 22

Graph Convolutional Networks with Dependency Parser towards ...

引用

22nd IEEE International Conference on Data Mining (ICDM)

作者： Yang, Minqiang Liu, Xinqi Mao, Chengsheng Hu, Bin Lanzhou Univ Sch Informat Sci & Engn Lanzhou Peoples R China Northwestern Univ Dept Prevent Med Feinberg Sch Med Chicago IL USA

ISBN: (纸本)9798350346091

Sentiment analysis has become increasingly important in natural language processing (NLP). Recent efforts have been devoted to the graph convolutional network (GCN) due to its advantages in handling the complex information. However, the improvement of GCN in NLP is hindered because the pretrained word vectors do not fit well in various contexts and the traditional edge building methods are not suited well for the long and complex context. To address these problems, we propose the LSTM-GCN model to contextualize the pretrained word vectors and extract the sentiment representations from the complex texts. Particularly, LSTM-GCN captures the sentiment feature representations from multiple different perspectives including context and syntax. In addition to extracting contextual representation from pretrained word vectors, we utilize the dependency parser to analyse the dependency correlation between each word to extract the syntax representation. For each text, we build a graph with each word in the text as a node. Besides the edges between the neighboring words, we also connect the nodes with dependency correlation to capture syntax representations. Moreover, we introduce the message passing mechanism (MPM) which allows the nodes to update their representation by extract information from its neighbors. Also, to improve the message passing performance, we set the edges to be trainable and initialize the edge weights with the pointwise mutual information (PMI) method. The results of the experiments show that our LSTM-GCN model outperforms several state-of-the-art models. And extensive experiments validate the rationality and effectiveness of our model.

关键词： Sentiment Analysis multiview representation learning GCN LSTM Dependency Parser

来源：评论

学校读者我要写书评

暂无评论

Autoencoder in Autoencoder Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2024年第2期35卷 2263-2275页

作者： Zhang, Changqing Geng, Yu Han, Zongbo Liu, Yeqing Fu, Huazhu Hu, Qinghua Tianjin Univ Tianjin Key Lab Machine Learning Tianjin 300350 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China ASTAR Inst High Performance Comp IHPC Singapore 138632 Singapore

Modeling complex correlations on multiview data is still challenging, especially for high-dimensional features with possible noise. To address this issue, we propose a novel unsupervised multiview representation learning (UMRL) algorithm, termed autoencoder in autoencoder networks (AE(2)-Nets). The proposed framework effectively encodes information from high-dimensional heterogeneous data into a compact and informative representation with the proposed bidirectional encoding strategy. Specifically, the proposed AE(2)-Nets conduct encoding in two directions: the inner-AE-networks extract view-specific intrinsic information (forward encoding), while the outer-AE-networks integrate this view-specific intrinsic information from different views into a latent representation (backward encoding). For the nested architecture, we further provide a probabilistic explanation and extension from hierarchical variational autoencoder. The forward-backward strategy flexibly addresses high-dimensional (noisy) features within each view and encodes complementarity across multiple views in a unified framework. Extensive results on benchmark datasets validate the advantages compared to the state-of-the-art algorithms.

关键词： Bidirectional encoding complete representation multiview representation learning

来源：评论

学校读者我要写书评

暂无评论

Joint Versus Independent multiview Hashing for Cross-View Retrieval

引用

IEEE TRANSACTIONS ON CYBERNETICS 2021年第10期51卷 4982-4993页

作者： Hu, Peng Peng, Xi Zhu, Hongyuan Lin, Jie Zhen, Liangli Peng, Dezhong Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Agcy Sci Technol & Res Inst Infocomm Res Singapore Singapore Agcy Sci Technol & Res Inst High Performance Comp Singapore Singapore Frontier Acad Ctr Shenzhen Peng Cheng Lab Shenzhen 518052 Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China

Thanks to the low storage cost and high query speed, cross-view hashing (CVH) has been successfully used for similarity search in multimedia retrieval. However, most existing CVH methods use all views to learn a common Hamming space, thus making it difficult to handle the data with increasing views or a large number of views. To overcome these difficulties, we propose a decoupled CVH network (DCHN) approach which consists of a semantic hashing autoencoder module (SHAM) and multiple multiview hashing networks (MHNs). To be specific, SHAM adopts a hashing encoder and decoder to learn a discriminative Hamming space using either a few labels or the number of classes, that is, the so-called flexible inputs. After that, MHN independently projects all samples into the discriminative Hamming space that is treated as an alternative ground truth. In brief, the Hamming space is learned from the semantic space induced from the flexible inputs, which is further used to guide view-specific hashing in an independent fashion. Thanks to such an independent/decoupled paradigm, our method could enjoy high computational efficiency and the capacity of handling the increasing number of views by only using a few labels or the number of classes. For a newly coming view, we only need to add a view-specific network into our model and avoid retraining the entire model using the new and previous views. Extensive experiments are carried out on five widely used multiview databases compared with 15 state-of-the-art approaches. The results show that the proposed independent hashing paradigm is superior to the common joint ones while enjoying high efficiency and the capacity of handling newly coming views.

关键词： Semantics Decoding Training Computer science Kernel Logistics Cybernetics Common hamming space cross-view retrieval decoupled cross-view hashing network (DCHN) multiview hashing multiview representation learning

来源：评论

学校读者我要写书评

暂无评论

Canonical Correlation Analysis With L2,1-Norm for multiview Data representation

引用

IEEE TRANSACTIONS ON CYBERNETICS 2020年第11期50卷 4772-4782页

作者： Xu, Meixiang Zhu, Zhenfeng Zhang, Xingxing Zhao, Yao Li, Xuelong Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Key Lab Adv Informat Sci & Network Techno Beijing 100044 Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Northwestern Polytech Univ Ctr Opt Imagery Anal & Learning Xian 710072 Peoples R China

For many machine learning algorithms, their success heavily depends on data representation. In this paper, we present an l(2,1)-norm constrained canonical correlation analysis (CCA) model, that is, L-2,L-1-CCA, toward discovering compact and discriminative representation for the data associated with multiple views. To well exploit the complementary and coherent information across multiple views, the l(2,1)-norm is employed to constrain the canonical loadings and measure the canonical correlation loss term simultaneously. It enables, on the one hand, the canonical loadings to be with the capacity of variable selection for facilitating the interpretability of the learned canonical variables, and on the other hand, the learned canonical common representation keeps highly consistent with the most canonical variables from each view of the data. Meanwhile, the proposed L-2,L-1-CCA can also be provided with the desired insensitivity to noise (outliers) to some degree. To solve the optimization problem, we develop an efficient alternating optimization algorithm and give its convergence analysis both theoretically and experimentally. Considerable experiment results on several realworld datasets have demonstrated that L-2,L-1-CCA can achieve competitive or better performance in comparison with some representative approaches for multiview representation learning.

关键词： Canonical correlation analysis (CCA) l(2,1)-norm multiview representation learning shared subspace sparse learning

来源：评论

学校读者我要写书评

暂无评论

CB2CF: A Neural multiview Content-to-Collaborative Filtering Model for Completely Cold Item Recommendations 19

CB2CF: A Neural Multiview Content-to-Collaborative Filtering...

引用

13th ACM Conference on Recommender Systems (RECSYS)

作者： Barkan, Oren Koenigstein, Noam Yogev, Eylon Katz, Ori Microsoft Herzliyya Israel Tel Aviv Univ Tel Aviv Israel Technion Haifa Israel

ISBN: (纸本)9781450362436

In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a "real-world" algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.

关键词： Cold item recommendations multiview representation learning

来源：评论

学校读者我要写书评

暂无评论

Variational graph autoencoders for multiview canonical correlation analysis

引用

SIGNAL PROCESSING 2021年 188卷 108182-108182页

作者： Kaloga, Yacouba Borgnat, Pierre Chepuri, Sundeep Prabhakar Abry, Patrice Habrard, Amaury Univ Lyon Univ Claude Bernard CNRS Ens LyonLab Phys Lyon France Indian Inst Sci Dept Elect & Commun Engn Bangalore Karnataka India Univ Lyon CNRS Lab Hubert Curien UJM St EtienneUMR 5516 F-5516 Lyon France

We present a novel approach for multiview canonical correlation analysis based on a variational graph neural network model. We propose a nonlinear model which takes into account the available graph based geometric constraints while being scalable to large-scale datasets with multiple views. This model combines the probabilistic interpretation of CCA with an autoencoder architecture based on graph convolutional neural network layers. Experiments with the proposed method are conducted on classification, clustering, and recommendation tasks on real datasets. The algorithm is competitive with state-of-the-art multiview representation learning techniques, in addition to being scalable and robust to instances with missing views. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Canonical correlation analysis Dimensionality reduction multiview representation learning Graph neurals networks Variational inference

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：