Multi-view Subspace Adaptive Learning via Autoencoder and Attention
- URL: http://arxiv.org/abs/2201.00171v1
- Date: Sat, 1 Jan 2022 11:31:52 GMT
- Title: Multi-view Subspace Adaptive Learning via Autoencoder and Attention
- Authors: Jian-wei Liu, Hao-jie Xie, Run-kun Lu, and Xiong-lin Luo
- Abstract summary: We propose a new Multiview Subspace Adaptive Learning based on Attention and Autoencoder (MSALAA)
This method combines a deep autoencoder and a method for aligning the self-representations of various views.
We empirically observe significant improvement over existing baseline methods on six real-life datasets.
- Score: 3.8574404853067215
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Multi-view learning can cover all features of data samples more
comprehensively, so multi-view learning has attracted widespread attention.
Traditional subspace clustering methods, such as sparse subspace clustering
(SSC) and low-ranking subspace clustering (LRSC), cluster the affinity matrix
for a single view, thus ignoring the problem of fusion between views. In our
article, we propose a new Multiview Subspace Adaptive Learning based on
Attention and Autoencoder (MSALAA). This method combines a deep autoencoder and
a method for aligning the self-representations of various views in Multi-view
Low-Rank Sparse Subspace Clustering (MLRSSC), which can not only increase the
capability to non-linearity fitting, but also can meets the principles of
consistency and complementarity of multi-view learning. We empirically observe
significant improvement over existing baseline methods on six real-life
datasets.
Related papers
- Towards Generalized Multi-stage Clustering: Multi-view Self-distillation [10.368796552760571]
Existing multi-stage clustering methods independently learn the salient features from multiple views and then perform the clustering task.
This paper proposes a novel multi-stage deep MVC framework where multi-view self-distillation (DistilMVC) is introduced to distill dark knowledge of label distribution.
arXiv Detail & Related papers (2023-10-29T03:35:34Z) - Multi-View Class Incremental Learning [57.14644913531313]
Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance.
This paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views.
arXiv Detail & Related papers (2023-06-16T08:13:41Z) - One-step Multi-view Clustering with Diverse Representation [47.41455937479201]
We propose a one-step multi-view clustering with diverse representation method, which incorporates multi-view learning and $k$-means into a unified framework.
We develop an efficient optimization algorithm with proven convergence to solve the resultant problem.
arXiv Detail & Related papers (2023-06-08T02:52:24Z) - Subspace-Contrastive Multi-View Clustering [0.0]
We propose a novel Subspace-Contrastive Multi-View Clustering (SCMC) approach.
We employ view-specific auto-encoders to map the original multi-view data into compact features perceiving its nonlinear structures.
To demonstrate the effectiveness of the proposed model, we conduct a large number of comparative experiments on eight challenge datasets.
arXiv Detail & Related papers (2022-10-13T07:19:37Z) - Adaptively-weighted Integral Space for Fast Multiview Clustering [54.177846260063966]
We propose an Adaptively-weighted Integral Space for Fast Multiview Clustering (AIMC) with nearly linear complexity.
Specifically, view generation models are designed to reconstruct the view observations from the latent integral space.
Experiments conducted on several realworld datasets confirm the superiority of the proposed AIMC method.
arXiv Detail & Related papers (2022-08-25T05:47:39Z) - Attentive Multi-View Deep Subspace Clustering Net [4.3386084277869505]
We propose a novel Attentive Multi-View Deep Subspace Nets (AMVDSN)
Our proposed method seeks to find a joint latent representation that explicitly considers both consensus and view-specific information.
The experimental results on seven real-world data sets have demonstrated the effectiveness of our proposed algorithm against some state-of-the-art subspace learning approaches.
arXiv Detail & Related papers (2021-12-23T12:57:26Z) - Tensor-based Intrinsic Subspace Representation Learning for Multi-view
Clustering [18.0093330816895]
We propose a novel-based Intrinsic Subspace Representation (TISRL) for multi-view clustering in this paper.
It can be seen that specific information contained in different views is fully investigated by the rank preserving decomposition.
Experimental results on nine common used real-world multi-view datasets illustrate the superiority of TISRL.
arXiv Detail & Related papers (2020-10-19T03:36:18Z) - Unsupervised Multi-view Clustering by Squeezing Hybrid Knowledge from
Cross View and Each View [68.88732535086338]
This paper proposes a new multi-view clustering method, low-rank subspace multi-view clustering based on adaptive graph regularization.
Experimental results for five widely used multi-view benchmarks show that our proposed algorithm surpasses other state-of-the-art methods by a clear margin.
arXiv Detail & Related papers (2020-08-23T08:25:06Z) - Embedded Deep Bilinear Interactive Information and Selective Fusion for
Multi-view Learning [70.67092105994598]
We propose a novel multi-view learning framework to make the multi-view classification better aimed at the above-mentioned two aspects.
In particular, we train different deep neural networks to learn various intra-view representations.
Experiments on six publicly available datasets demonstrate the effectiveness of the proposed method.
arXiv Detail & Related papers (2020-07-13T01:13:23Z) - Multi-view Deep Subspace Clustering Networks [64.29227045376359]
Multi-view subspace clustering aims to discover the inherent structure of data by fusing multiple views of complementary information.
We propose the Multi-view Deep Subspace Clustering Networks (MvDSCN), which learns a multi-view self-representation matrix in an end-to-end manner.
The MvDSCN unifies multiple backbones to boost clustering performance and avoid the need for model selection.
arXiv Detail & Related papers (2019-08-06T06:44:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.