Paper proposes SKCCA for sparse kernel CCA, improving sparsity and reducing overfitting.
problem Lack of sparsity in kernel CCA solutions.
method Introduces SKCCA using ℓ1-regularization to penalize the dual vectors for sparsity. result Demonstrates improved sparsity and reduced overfitting in kernel CCA.
Canonical Correlation Analysis (CCA) is a classical tool for finding correlations among the components of two random vectors. In recent years, CCA has been widely applied to the analysis of genomic data, where it is common for researchers to perform multiple assays on a single set of patient samples. Recent work has pr…
We present a novel method for solving Canonical Correlation Analysis (CCA) in a sparse convex framework using a least squares approach. The presented method focuses on the scenario when one is interested in (or limited to) a primal representation for the first view while having a dual representation for the second view…
Kernel and MKCCA classify schizophrenia patients from imaging and genetic data.
problem Classifying schizophrenia patients from imaging and genetic data.
method Employed Kernel and Multiple Kernel Canonical Correlation Analysis (CCA) for classification.
result Kernel and Multiple Kernel CCA significantly outperform regularized linear CCA in classification accuracy.
Proposes ℓ0-CCA for sparse CCA with improved representation learning.
problem CCA models break with too many variables, and sparsity is beneficial.
method Sparse CCA with stochastic gates and ℓ0-regularization. result Improves representation learning by gating nuisance variables.
Robust kernel CCA method detects outliers and improves performance.
problem Kernel CO and CCO sensitivity to contaminated data.
method Proposed robust kernel CO and CCO, derived IF for CCA, robust kernel CCA method.
result Robust kernel CCA method performs better than standard kernel CCA for ideal and contaminated data.
New method solves sparse PCA and CCA with guaranteed convergence.
problem Sparse PCA and CCA for large-scale data analysis.
method Alternating manifold proximal gradient method.
result Unified convergence analysis for the proposed method.
Paper introduces RMEN-CCA for multi-view unsupervised learning.
problem Combining multiple data views for unsupervised learning.
method Robust matrix elastic net (RMEN) integrated with canonical correlation analysis (CCA).
result RMEN-CCA outperforms state-of-the-art methods on multiple datasets.
Canonical correlation analysis (CCA) is a classical representation learning technique for finding correlated variables in multi-view data. Several nonlinear extensions of the original linear CCA have been proposed, including kernel and deep neural network methods. These approaches seek maximally correlated projections …
Given two sets of variables, derived from a common set of samples, sparse Canonical Correlation Analysis (CCA) seeks linear combinations of a small number of variables in each set, such that the induced canonical variables are maximally correlated. Sparse CCA is NP-hard. We propose a novel combinatorial algorithm for s…
Paper proposes ASCCA for sparse CCA with trace Lasso regularization.
problem Sparse CCA in high-dimensional settings with correlated variables.
method Trace Lasso regularization, reformulated to Riemannian manifolds, inexact augmented Lagrangian method.
result Improved stability and interpretation of sparse CCA.
Imaging genetic research has essentially focused on discovering unique and co-association effects, but typically ignoring to identify outliers or atypical objects in genetic as well as non-genetics variables. Identifying significant outliers is an essential and challenging issue for imaging genetics and multiple source…
Sparse Canonical Correlation Analysis (CCA) has received considerable attention in high-dimensional data analysis to study the relationship between two sets of random variables. However, there has been remarkably little theoretical statistical foundation on sparse CCA in high-dimensional settings despite active methodo…
Proposes GCCA for detecting latent relations in multiview data with sparse structures.
problem Sparse CCA limitations for multiple datasets.
method Developed a GCCA algorithm based on distributed alternating iteration approach.
result Demonstrated effectiveness on synthetic and real-world datasets.
RKUM is an R package for robust kernel-based unsupervised methods.
problem Robust analysis under contaminated or noisy data conditions.
method Robust kernel covariance and cross-covariance operators using generalized loss functions.
result RKUM reduces sensitivity to contamination and effectively identifies outliers.
Canonical correlation analysis (CCA) is a valuable method for interpreting cross-covariance across related datasets of different dimensionality. There are many potential applications of CCA to neuroimaging data analysis. For instance, CCA can be used for finding functional similarities across fMRI datasets collected fr…
Bayesian method improves sparse CCA for multi-view data.
problem Integrative statistical analysis of multi-view high-dimensional data.
method Bayesian infinite factor model with graphical horseshoe prior or diagonal structure to encourage sparsity.
result The proposed Bayesian ScSCCA approach achieves robust estimation of sparse CCA.
To the best of our knowledge, there are no general well-founded robust methods for statistical unsupervised learning. Most of the unsupervised methods explicitly or implicitly depend on the kernel covariance operator (kernel CO) or kernel cross-covariance operator (kernel CCO). They are sensitive to contaminated data, …
Proposes PSCCA for estimating correlations and canonical correlations in sparse count data.
problem Estimating correlations and canonical correlations in sparse count data from next-generation sequencing.
method Probabilistic approach for sparse count data sets (PSCCA).
result PSCCA outperforms other methods in estimating true correlations and canonical correlations at the natural parameter level.
Canonical Correlation Analysis (CCA) is a widely used statistical tool with both well established theory and favorable performance for a wide range of machine learning problems. However, computing CCA for huge datasets can be very slow since it involves implementing QR decomposition or singular value decomposition of h…
New similarity index avoids limitations of CCA in neural networks.
problem Limitations of existing methods in measuring neural network representation similarity.
method Introducing a similarity index based on centered kernel alignment (CKA) to measure representational similarity matrices.
result CKA reliably identifies correspondences between representations in networks trained from different initializations.
ORCCA improves CCA performance with randomized features.
problem Improving CCA performance with randomized features.
method Proposes a task-specific scoring rule for selecting random features in CCA.
result ORCCA outperforms Kernel CCA in expectation.
In genome-wide interaction studies, to detect gene-gene interactions, most methods are divided into two folds: single nucleotide polymorphisms (SNP) based and gene-based methods. Basically, the methods based on the gene are more effective than the methods based on a single SNP. Recent years, while the kernel canonical …
Sparse CCA improves classical CCA for high-dimensional data.
problem High-dimensional data limits classical CCA's effectiveness.
method Sparse CCA with l1 constraints and ADMM for efficient solution.
result Efficiently solved sparse CCA using ADMM and TFOCS.
New sparse CCA method finds interpretable associations in multi-view data.
problem Discovering interpretable associations in high-dimensional multi-view data.
method Inspired by sparse PCA, proposed a convex maximization program equivalent to non-convex sparse CCA formulation, using gradient method to reduce search space.
result Proposed two-step algorithm and new sparse CCA variants (Directed Sparse CCA, Multi-View sCCA) for multi-omic studies.
Proposes FDR-corrected sparse CCA for neuroimaging and genomics.
problem High-dimensional datasets in neuroimaging and genomics make false discoveries a concern.
method FDR-corrected sparse canonical correlation analysis (CCA) for high-dimensional settings.
result The proposed method controls the FDR of canonical vectors in high-dimensional settings.
A novel graph-regularized CCA approach for datasets with a common source graph.
problem Discovering hidden sources in datasets with common geometry.
method Graph regularizer to encode common sources' geometry in CCA.
result Improved classification performance over competing methods.
New methods integrate nonlinear, sparse, and multi-view aspects for high-dimensional data analysis.
problem Integrating nonlinear dependence, sparsity, and multi-view data in high-dimensional datasets.
method Proposes HSIC-SGCCA, SA-KGCCA, and TS-KGCCA methods for multi-view high-dimensional data analysis.
result HSIC-SGCCA outperforms competing methods in multi-view variable selection.
A new method for identifying significant gene subsets improves disease prediction.
problem Identifying significant subsets of genes for disease prediction.
method Kernel gene shaving using influence function of kernel CCA.
result The proposed method outperformed three popular gene selection methods.
Quantum-inspired CCA improves correlation analysis for high-dimensional data.
problem High-dimensional data limits conventional CCA due to time complexity.
method Developed a quantum-inspired CCA (qiCCA) with logarithmic time complexity.
result qiCCA extracts more correlations than linear CCA and is comparable to deep and kernel CCA.
BLOCCS improves sparse CCA for better interpretation of multi-omics data.
problem Improving interpretation of multi-omics data.
method Block Sparse Canonical Correlation Analysis (BLOCCS) using a bi-convex objective and gradient descent.
result BLOCCS provides more interpretable solutions with improved orthogonality of sparse directions.
New method estimates sparse canonical vectors efficiently.
problem Sparse canonical vectors estimation in CCA.
method Quasi-Bayesian estimation via Rayleigh quotient function.
result Achieves minimax rate with low computational cost.
Kernel methods detect coherent structures in dynamical data.
problem Detecting coherent structures in complex dynamical systems.
method Kernel-based dimensionality reduction techniques and eigendecompositions of RKHS operators.
result Coherent sets of particle trajectories can be computed by kernel CCA.
In this paper, we consider the sparse eigenvalue problem wherein the goal is to obtain a sparse solution to the generalized eigenvalue problem. We achieve this by constraining the cardinality of the solution to the generalized eigenvalue problem and obtain sparse principal component analysis (PCA), sparse canonical cor…
New method finds linear relationships across multiple data blocks using proximal gradient descent with ℓ1 constraint.
problem Finding leading generalized eigenvectors for multi-block CCA.
method Proximal gradient descent with ℓ1 constraint. result Rate-optimal solution under suitable assumptions.
New insights into nonlinear multiview analysis for better data interpretation.
problem Identify shared latent components across different data views.
method Post-nonlinear model and multiview mixture learning.
result Identifies shared latent components under certain conditions.
In this paper, we address the problem of hidden common variables discovery from multimodal data sets of nonlinear high-dimensional observations. We present a metric based on local applications of canonical correlation analysis (CCA) and incorporate it in a kernel-based manifold learning technique.We show that this metr…
DTCCA learns nonlinear transformations of multi-view data for high-order correlation.
problem Learning complex nonlinear transformations of multiple data views.
method Maximizes high-order canonical correlation by jointly learning transformations of each view using a reformulated tensor decomposition.
result DTCCA efficiently handles high-dimensional and large number of views, overcoming scalability issues.
Unified CCA methods for large-scale data with fast SGD algorithms.
problem Computational infeasibility of classical CCA methods for large-scale data.
method Unconstrained objective, stochastic gradient descent (SGD) algorithms.
result Significantly faster convergence and higher correlations than previous methods.
Paper extends CCA for multiview learning, improving performance.
problem Learning representations across multiple data views.
method Extends CCA to a multiview mixture model with heuristics.
result Improves performance on downstream tasks compared to standard CCA.
End-to-end CCA optimizes both discriminative and latent space projections for multi-view learning.
problem Lack of class label information in CCA for multi-view learning tasks.
method Simultaneously optimizes a CCA-based and a task objective in an end-to-end manner to learn a non-linear CCA projection.
result Significant improvement in cross-view classification, regularization with a second view, and semi-supervised learning.
Unsupervised two-view learning, or detection of dependencies between two paired data sets, is typically done by some variant of canonical correlation analysis (CCA). CCA searches for a linear projection for each view, such that the correlations between the projections are maximized. The solution is invariant to any lin…
Proposes a probabilistic CCA with implicit distributions for multi-view data.
problem Overcoming the deficiency of linear correlation in practical multi-view learning tasks.
method Probabilistic interpretation of CCA based on implicit distributions, using Conditional Mutual Information (CMI) and Adversarial CCA (ACCA).
result Achieves superior alignment of multi-view data with implicit distributions.
Sparse GCA finds linear relationships in multiple datasets, using gradient descent.
problem Finding linear relationships across multiple datasets with sparse loading vectors.
method Formulated as generalized eigenvalue problems, used a thresholded gradient descent algorithm.
result Proposed algorithm yields tight estimation error bounds and demonstrates effectiveness on synthetic datasets.
We present an extension of sparse Canonical Correlation Analysis (CCA) designed for finding multiple-to-multiple linear correlations within a single set of variables. Unlike CCA, which finds correlations between two sets of data where the rows are matched exactly but the columns represent separate sets of variables, th…
Paper tackles fairness in CCA by minimizing correlation disparity error.
problem Fairness issues in CCA.
method Framework to minimize correlation disparity error in CCA.
result Reduces correlation disparity error without sacrificing CCA accuracy.
New measures link neural representation geometry to decoding ability.
problem Understanding how neural representations relate to decoding ability.
method Showed that popular similarity measures can be interpreted from a decoding perspective.
result Proved that measures like CKA and CCA quantify alignment between optimal linear readouts.
SWCCA identifies specific subsets of samples for better correlation analysis.
problem Identify specific subsets of samples contributing to correlation between two data matrices.
method Proposes SWCCA with weights to regularize different samples, solves using alternating iterative algorithm.
result Demonstrates effectiveness and superiority over related methods on synthetic and real-world data.