Deep Generalized Canonical Correlation Analysis

Benton, Adrian; Khayrallah, Huda; Gujral, Biman; Reisinger, Dee Ann; Zhang, Sheng; Arora, Raman

doi:10.18653/v1/w19-4301

Cited by 90 publications

(96 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CCA has been successfully employed effectively in other contexts to integrate highdimensional biological data 66,65 . Penalized CCA 67 and deep CCA 68,69 can produce non-linear variates and may prove to be highly effective as we confront higher throughput platforms with greater cell-to-cell data.…”

Section: Discussionmentioning

confidence: 99%

Defining Inflammatory Cell States in Rheumatoid Arthritis Joint Synovial Tissues by Integrating Single-cell Transcriptomics and Mass Cytometry

Zhang

Wei

Slowikowski

et al. 2018

Preprint

169

371

View full text Add to dashboard Cite

Wei, Slowikowski, Fonseka, Rao et al A single cell map of the RA joint Abstract 78 To define the cell populations in rheumatoid arthritis (RA) driving joint inflammation, we applied 79 single-cell RNA-seq (scRNA-seq), mass cytometry, bulk RNA-seq, and flow cytometry to sorted 80 T cells, B cells, monocytes, and fibroblasts from 51 synovial tissue RA and osteoarthritis (OA) 81 patient samples. Utilizing an integrated computational strategy based on canonical correlation 82 analysis to 5,452 scRNA-seq profiles, we identified 18 unique cell populations. Combining mass 83 cytometry and transcriptomics together revealed cell states expanded in RA synovia: 84 THY1 + HLA high sublining fibroblasts (OR=33.8), IL1B + pro-inflammatory monocytes (OR=7.8), 85 CD11c + T-bet + autoimmune-associated B cells (OR=5.7), and PD-1 + Tph/Tfh (OR=3.0). We also 86 defined CD8 + T cell subsets characterized by GZMK + , GZMB + , and GNLY + expression. Using 87 bulk and single-cell data, we mapped inflammatory mediators to source cell populations, for 88 example attributing IL6 production to THY1 + HLA high fibroblasts and naïve B cells, and IL1B to 89 pro-inflammatory monocytes. These populations are potentially key mediators of RA 90 pathogenesis. 91 92 93 94 95 96 97 98 99 100

show abstract

Section: Discussionmentioning

confidence: 99%

Defining Inflammatory Cell States in Rheumatoid Arthritis Joint Synovial Tissues by Integrating Single-cell Transcriptomics and Mass Cytometry

Zhang

Wei

Slowikowski

et al. 2018

Preprint

169

371

View full text Add to dashboard Cite

show abstract

“…One finds linear transformations {U j ∈ R dj ×k } J j=1 , that minimize the mutual reconstruction error under constraints, in a way equivalent to maximizing correlation. This framework can be extended to non-linear feature extractors [29] with the objective:…”

Section: Extensions Of Ccamentioning

confidence: 99%

Learning from Multiview Correlations in Open-domain Videos

Holzenberger

Palaskar

Madhyastha

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the existence of a latent alignment between views, such as between speech and its transcription, and by the multitude of choices for the learning objective. We explore an advanced, correlation-based representation learning method on a 4-way parallel, multimodal dataset, and assess the quality of the learned representations on retrieval-based tasks. We show that the proposed approach produces rich representations that capture most of the information shared across views. Our best models for speech and textual modalities achieve retrieval rates from 70.7% to 96.9% on open-domain, user-generated instructional videos. This shows it is possible to learn reliable representations across disparate, unaligned and noisy modalities, and encourages using the proposed approach on larger datasets.Index Terms-Multiview Learning, Representation Learning, Canonical Correlation Analysis * Equal contribution in its Portuguese translation. Figure 1 shows an overview of our learning algorithm with 4 different input views, detailed in Section 3.Given these multiple parallel modalities, we address the following: how much information is shared across modalities? How can we learn a representation that captures information from all modalities? We measure this using intrinsic evaluations. In the remainder of this paper, we describe related work, then the proposed methods and our experimental setup, and finally present our results. CCA loss neural network English speech neural network video neural network Once I have my jack stand there on the rear axle, go ahead and release the hydraulic pressure.. English text neural network Q u a n d o e u t i v e r m e u macaco parado no eixo traseiro, vá em frente e libere a pressão hidráulica.

show abstract

“…More recently, several deep neural network (DNN)-based algorithms have been proposed for nonlinear feature representation learning on multi-view problems [13], [14]. A deep model for CCA estimation, referred to as deep CCA (DCCA), has also been proposed [15], [16]. Like CCA, DCCA is a parametric approach and is scalable to large datasets, and like KCCA, it can model nonlinearity in the data.…”

Section: Previous Workmentioning

confidence: 99%

Semi-supervised Deep Representation Learning for Multi-View Problems

Noroozi

Bahaadini

Zheng

et al. 2018

2018 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small amount of labeled data is not well-studied. We introduce a semisupervised neural network model, named Multi-view Discriminative Neural Network (MDNN), for multi-view problems. MDNN finds nonlinear view-specific mappings by projecting samples to a common feature space using multiple coupled deep networks. It is capable of leveraging both labeled and unlabeled data to project multi-view data so that samples from different classes are separated and those from the same class are clustered together. It also uses the inter-view correlation between views to exploit the available information in both the labeled and unlabeled data. Extensive experiments conducted on four datasets demonstrate the effectiveness of the proposed algorithm for multi-view semisupervised learning.

show abstract

Deep Generalized Canonical Correlation Analysis

Cited by 90 publications

References 17 publications

Defining Inflammatory Cell States in Rheumatoid Arthritis Joint Synovial Tissues by Integrating Single-cell Transcriptomics and Mass Cytometry

Defining Inflammatory Cell States in Rheumatoid Arthritis Joint Synovial Tissues by Integrating Single-cell Transcriptomics and Mass Cytometry

Learning from Multiview Correlations in Open-domain Videos

Semi-supervised Deep Representation Learning for Multi-View Problems

Contact Info

Product

Resources

About