DMIB: Dual-Correlated Multivariate Information Bottleneck for Multiview Clustering

Hu, Shizhe; Shi, Zenglin; Ye, Yangdong

doi:10.1109/tcyb.2020.3025636

Cited by 23 publications

(21 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where in (11), we use the short-hand notation {p k+1 <i } := {p k+1 l } i−1 l=1 to denote the primal variables, up to i − 1 views that are already updated to the (k + 1) st step, and {p k i< } := {p k m } V m=i+1 to denote the rest that are still at the k th step. We define {p k+1 <0 } = {∅} = {p k >V }; in (11) and ( 12), the superscript k denotes the step index; each of Ω i , Ω q , Π (i)…”

Section: A Consensus-complement Formmentioning

confidence: 99%

“…Finally the difference between the primal and augmented variables are added to the dual variables (11c) to complete the k th iteration. After convergence of (11), we run (12) in similar fashion for each view. And this completes the full algorithm.…”

Section: A Consensus-complement Formmentioning

confidence: 99%

“…The tensor is the primal variable for step i which belongs to a compound simplex Ω (i) . In the algorithm, for each step (15a), we solve it with (11) by setting V = 1 and treating the estimators from the previous steps as priors. This can be easily shown through Bayes' rule and the conditional independence assumption.…”

Section: B Incremental Update Formmentioning

confidence: 99%

“…In [10], each view was treated as a single-view IB problem followed by a post-processing stage that aims to maximize the mutual information between the view-specific representations to encourage agreement of clustering hypotheses. More recently, [11] proposed a bottom-up, heuristic multiview IB objective which maximizes view-specific information, view-shared information, and inter-cluster correlation while compressing the observations simultaneously. In solving the overall objective, the authors resort to greedy solvers and select the best result from a set of off-the-shelf algorithms [12].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On the Multi-View Information Bottleneck Representation

Huang¹,

Gamal²,

Gamal³

2022

Preprint

View full text Add to dashboard Cite

In this work, we generalize the information bottleneck (IB [1]) approach to the multi-view learning context. The exponentially growing complexity of the optimal representation motivates the development of two novel formulations with more favorable performance-complexity tradeoffs. The first approach is based on forming a stochastic consensus and is suited for scenarios with significant representation overlap between the different views. The second method, relying on incremental updates, is tailored for the other extreme scenario with minimal representation overlap. In both cases, we extend our earlier work on the alternating directional methods of multiplier (ADMM [2]) solver and establish its convergence and scalability. Empirically, we find that the proposed methods outperform state-of-the-art approaches in multi-view classification problems under a broad range of modelling parameters.

show abstract

Section: A Consensus-complement Formmentioning

confidence: 99%

Section: A Consensus-complement Formmentioning

confidence: 99%

Section: B Incremental Update Formmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the Multi-View Information Bottleneck Representation

Huang¹,

Gamal²,

Gamal³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Fusion visual-tactile information could improve the clustering performance effectively, since they can provide complementary information. Generally, most existing VTFC methods mainly utilize the idea of multi-view clustering (Dang et al 2020;Hu, Shi, and Ye 2020;Hu, Yan, and Ye 2020), e.g., Zhang et al (Zhang et al 2020) propose a VTFC model based on non-negative matrix factorization (NMF) as well as consensus clustering and achieve great progresses. As far as we know, this is the first work about visual-tactile fused clustering.…”

Section: Introductionmentioning

confidence: 99%

Visual Tactile Fusion Object Clustering

Zhang

Cong

Sun

et al. 2020

AAAI

View full text Add to dashboard Cite

Object clustering, aiming at grouping similar objects into one cluster with an unsupervised strategy, has been extensively-studied among various data-driven applications. However, most existing state-of-the-art object clustering methods (e.g., single-view or multi-view clustering methods) only explore visual information, while ignoring one of most important sensing modalities, i.e., tactile information which can help capture different object properties and further boost the performance of object clustering task. To effectively benefit both visual and tactile modalities for object clustering, in this paper, we propose a deep Auto-Encoder-like Non-negative Matrix Factorization framework for visual-tactile fusion clustering. Specifically, deep matrix factorization constrained by an under-complete Auto-Encoder-like architecture is employed to jointly learn hierarchical expression of visual-tactile fusion data, and preserve the local structure of data generating distribution of visual and tactile modalities. Meanwhile, a graph regularizer is introduced to capture the intrinsic relations of data samples within each modality. Furthermore, we propose a modality-level consensus regularizer to effectively align the visual and tactile data in a common subspace in which the gap between visual and tactile data is mitigated. For the model optimization, we present an efficient alternating minimization strategy to solve our proposed model. Finally, we conduct extensive experiments on public datasets to verify the effectiveness of our framework.

show abstract

Incomplete multi-view partial multi-label classification via deep semantic structure preservation

Li,

Wu,

Peng

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Recent advances in multi-view multi-label learning are often hampered by the prevalent challenges of incomplete views and missing labels, common in real-world data due to uncertainties in data collection and manual annotation. These challenges restrict the capacity of the model to fully utilize the diverse semantic information of each sample, posing significant barriers to effective learning. Despite substantial scholarly efforts, many existing methods inadequately capture the depth of semantic information, focusing primarily on shallow feature extractions that fail to maintain semantic consistency. To address these shortcomings, we propose a novel Deep semantic structure-preserving (SSP) model that effectively tackles both incomplete views and missing labels. SSP innovatively incorporates a graph constraint learning (GCL) scheme to ensure the preservation of semantic structure throughout the feature extraction process across different views. Additionally, the SSP integrates a pseudo-labeling self-paced learning (PSL) strategy to address the often-overlooked issue of missing labels, enhancing the classification accuracy while preserving the distribution structure of data. The SSP model creates a unified framework that synergistically employs GCL and PSL to maintain the integrity of semantic structural information during both feature extraction and classification phases. Extensive evaluations across five real datasets demonstrate that the SSP method outperforms existing approaches, including lrMMC, MVL-IV, MvEL, iMSF, iMvWL, NAIML, and DD-IMvMLC-net. It effectively mitigates the impacts of data incompleteness and enhances semantic representation fidelity.

show abstract

DMIB: Dual-Correlated Multivariate Information Bottleneck for Multiview Clustering

Cited by 23 publications

References 66 publications

On the Multi-View Information Bottleneck Representation

On the Multi-View Information Bottleneck Representation

Visual Tactile Fusion Object Clustering

Incomplete multi-view partial multi-label classification via deep semantic structure preservation

Contact Info

Product

Resources

About