Unsupervised representation learning based on the deep multi-view ensemble learning

Koohzadi, Maryam; Charkari, Nasrollah Moghadam; Ghaderi, Foad

doi:10.1007/s10489-019-01526-0

Cited by 16 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We set the hyper-parameters to minimize the reconstruction loss. During the phase of pre-training, we performed a basic tuning of the parameters following the common practices of previous studies [71,72]. We randomly initialized the weights of the layers.…”

Section: Resultsmentioning

confidence: 99%

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

Cotroneo,

De Simone,

Liguori

et al. 2021

Preprint

View full text Add to dashboard Cite

Identifying the failure modes of cloud computing systems is a difficult and time-consuming task, due to the growing complexity of such systems, and the large volume and noisiness of failure data. This paper presents a novel approach for analyzing failure data from cloud systems, in order to relieve human analysts from manually fine-tuning the data for feature engineering. The approach leverages Deep Embedded Clustering (DEC), a family of unsupervised clustering algorithms based on deep learning, which uses an autoencoder to optimize data dimensionality and inter-cluster variance. We applied the approach in the context of the OpenStack cloud computing platform, both on the raw failure data and in combination with an anomaly detection pre-processing algorithm. The results show that the performance of the proposed approach, in terms of purity of clusters, is comparable to, or in some cases even better than manually fine-tuned clustering, thus avoiding the need for deep domain knowledge and reducing the effort to perform the analysis. In all cases, the proposed approach provides better performance than unsupervised clustering when no feature engineering is applied to the data. Moreover, the distribution of failure modes from the proposed approach is closer to the actual frequency of the failure modes.

show abstract

Section: Resultsmentioning

confidence: 99%

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

Cotroneo,

De Simone,

Liguori

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, deep networks have achieved great success in feature learning problem on various computer vision applications. Many multiview learning methods are proposed based on deep networks, such as, deep multi-view ensemble model [35], deep multiview concept learning (DMCL) [36], graph regularized low-rank representation tensor and affinity matrix (GLTA) [37]. These multi-view fusion methods have been used to predict disease and analyze pathogenesis [38]- [40].…”

Section: Introductionmentioning

confidence: 99%

A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features

Zhang

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In many computer vision applications, one image can be represented by multiple heterogeneous features from different views, most of them commonly locate in high-dimensional space. These features can reflect different characteristics of one same object, they contain compatible and complementary information among each other. How to construct an uniform low-dimensional embedding features which represent useful information of multi-view features is still an important and urgent issue to be solved. Therefore, we propose a multi-view fusion method via tensor learning and gradient descent (MvF-TG) in this paper. MvF-TG reconstructs a low dimensional mapping subspace of each object by utilizing its k nearest neighbors, which preserves the underlying neighborhood structure of the original local manifold. The new method can effectively exploit the spatial correlation information from the multi-view features by tensor learning. Furthermore, the method constructs a gradient descent optimization model to generate the better unified low dimensional embedding. The proposed method is compared with several single-view and multi-view dimensional reduction methods in these indicators of P, R, MAP and F-measure. In the retrieval experiments, the P values of the new method respectively are 86.80%, 52.00%, 68.56% and 78.80% on datasets of Corel1k, Corel5k, Corel10k and Holidays. In the classification experiments, the mean accuracies of it respectively are 47.94% and 87.58% on datasets of Caltech101 and Coil. These values are higher than those obtained by other comparison methods, various evaluations based on the applications of image classification and retrieval demonstrate the effectiveness of our proposed method on multi-view feature fusion dimension reduction.

show abstract

“…Scholars have obtained feedback from 146 participants from online surveys which involve users' common activities, usage habits and motivation to join the group. Inheritance learning Koohzadi et al (2020) is a learning process of creating a new class on the basis of the existing class; since everyone has their own unique writing style, author signature recognition Elhoseny et al (2018) is divided into two types: online signature verification and offline signature verification, which can be conveniently provided by scientific research and academic network. Because most of the current research on academic text mining is based on vocabulary, window and full text, it often ignores the internal structure of academic text, leading to many ambiguity problems.…”

Section: Introductionmentioning

confidence: 99%

Collaborator recommendation integrating author’s cooperation strength and research interests on attributed graph

2021

Adv. in Comp. Int.

View full text Add to dashboard Cite

Collaborator recommendation aims to seek suitable collaborators for a given author. In this paper, we model all authors and their features as an attributed graph, and then perform community search on the attributed graph to locate the best collaborator community. From the early collaborative filtering-based methods to the recent deep learning-based methods, most existing works usually unilaterally weigh the network structure or node attributes, or directly search the community via the given node. We argue that the inherent disadvantage of these methods is that the quality of the node to be recommended may not be high, which can lead to suboptimal recommendation results. In this work, we develop a new recommendation framework, i.e., Collaborator Recommendation Integrating Author's Cooperation Strength and Research Interests (CRISI) on an attributed graph. It improves the quality of recommended node via double-weighting the structure and attributes as well as adopting the node replacement method. This can effectively recommend collaborators who have a close cooperative relationship with the recommended node. We conduct extensive experiments on two real-world datasets, and further analysis shows that the performance of our proposed CRISI model is superior to existing methods.

show abstract

Unsupervised representation learning based on the deep multi-view ensemble learning

Cited by 16 publications

References 40 publications

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features

Collaborator recommendation integrating author’s cooperation strength and research interests on attributed graph

Contact Info

Product

Resources

About