Journal Article10.1109/tmm.2022.3210376
Graph Contrastive Partial Multi-View Clustering
32
TL;DR: In this article , an augmentation-free graph contrastive learning framework is proposed to solve the problem of partial multi-view clustering, where the representations of similar samples (i.e., belonging to the same cluster) should be similar.
read more
Abstract: With the diversity of information acquisition, data is stored and transmitted in an increasing number of modalities. Nevertheless, it is not unusual for parts of the data to be lost in some views due to unavoidable acquisition, transmission or storage errors. In this paper, we propose an augmentation-free graph contrastive learning framework to solve the problem of partial multi-view clustering. Notably, we suppose that the representations of similar samples (i.e., belonging to the same cluster) should be similar. This is distinct from the general unsupervised contrastive learning that assumes an image and its augmentations share a similar representation. Specifically, relation graphs are constructed using the nearest neighbors to identify existing similar samples, then the constructed inter-instance relation graphs are transferred to the missing views to build graphs on the corresponding missing data. Subsequently, two main components, within-view graph contrastive learning and cross-view graph consistency learning, are devised to maximize the mutual information of different views within a cluster. The proposed approach elevates instance-level contrastive learning and missing data inference to the cluster-level, effectively mitigating the impact of individual missing data on clustering. Experiments on several challenging datasets demonstrate the superiority of our proposed methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Deep Multiview Clustering by Contrasting Cluster Assignments
TL;DR: In this article , a cross-view contrastive learning (CVCL) method was proposed to learn view-invariant representations and produce clustering results by contrasting the cluster assignments among multiple views.
Deep Incomplete Multi-View Clustering with Cross-View Partial Sample and Prototype Alignment
Jiaqi Jin,Siwei Wang,Zhibin Dong,Xinwang Liu,En Zhu +4 more
- 01 Jun 2023
TL;DR: Deep Incomplete Multi-View Clustering with Cross-View Partial Sample and Prototype Alignment achieves effective clustering despite incomplete samples and biased prototypes.
29
Manifold-based Incomplete Multi-view Clustering via Bi-Consistency Guidance
Huibing Wang,Mingze Yao,Yawei Chen,Yunqiu Xu,Haipeng Liu,Wei Jia,Xianping Fu,Yang Wang +7 more
TL;DR: This paper proposes Manifold-based Incomplete Multi-view Clustering via Bi-consistency guidance (MIMB), a novel method that recovers incomplete data among various views, balances discrepancies, and achieves biconsistency guidance via reverse regularization for superior clustering results.
29
Deep Multiview Clustering by Contrasting Cluster Assignments
Jie Chen,Hua Mao,Wai Lok Woo,Xi Peng +3 more
- 01 Oct 2023
TL;DR: Deep Multiview Clustering by Contrasting Cluster Assignments learns view-invariant representations and produces clustering results by contrasting cluster assignments among multiple views.
27
EDMC: Efficient Multi-view Clustering via Cluster and Instance Space Learning
Ya Qin,Nan Pu,Hanzhou Wu +2 more
TL;DR: EDMC efficiently clusters multi-view data by learning informative anchors from cluster and instance space representations, achieving low time and space complexity.
18
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
•Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
•Posted Content
A Simple Framework for Contrastive Learning of Visual Representations
TL;DR: It is shown that composition of data augmentations plays a critical role in defining effective predictive tasks, and introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning.