This work optimizes induced correlation in joint graph embeddings.
problem Optimizing correlation across embedded networks in joint graph embeddings.
method Developed corr2Omni algorithm to estimate optimal Omnibus weights.
result corr2Omni algorithm improves inference fidelity compared to classical Omnibus construction.
New method detects and analyzes correlation in multiple network data.
problem Detecting and analyzing correlation in multiple network data.
method Generalized omnibus embedding methodology.
result Induced correlation can significantly extend the reach of spectral inference procedures.
Proposes a hierarchical clustering method for positive and negative dissimilarities.
problem Clustering dissimilarities, especially positive and negative.
method Hierarchical correlation clustering followed by tree preserving embedding.
result Performance on various datasets.
The study analyzes XRP transaction networks to understand market dynamics.
problem Understanding market dynamics of XRP through transaction data.
method Weekly weighted directed networks are embedded into a vector space using network embedding techniques. A correlation tensor is calculated and analyzed using singular value decomposition.
result The correlation tensor provides insights into the system's behavior and dependence on model parameters.
A new neural network model ONCF improves collaborative filtering by explicitly modeling embedding correlations.
problem Improving collaborative filtering for better recommendation quality.
method ONCF uses an outer product to model embedding correlations and a convolutional layer to learn high-order correlations.
result ONCF outperforms existing models in implicit feedback data experiments.
ImplicitCE recommends items to new users by co-embedding users and items.
problem Recommendation for new users with no feedback structure.
method End-to-end learning of embedding spaces and transformation function, maximizing correlations between model predictions and user affinities.
result ImplicitCE outperforms state-of-the-art algorithms on Twitter and DBLP datasets.
Algorithm learns stock correlation matrix embedding using graph machine learning.
problem Understanding complex relationships among stocks based on their correlation matrix.
method Proposes a graph machine learning approach called Node2Vec to compress the correlation network into an embedding.
result The algorithm can learn an embedding from the correlation network of S&P 500 stock data.
New method embeds correlation networks to reveal underlying time series patterns.
problem Analyzing correlation networks derived from time series data.
method Spectral embedding of noisy correlation networks, leveraging Fourier basis elements.
result Spectral embedding recovers true vertex-level latent representations under suitable assumptions.
Proposes ACCA for better alignment of multiple data perspectives.
problem Unclear alignment between multiple data perspectives.
method Iteratively solves alignment and multi-view embedding.
result Improved alignment and embedding of multiple data perspectives.
MPVAE learns latent embeddings and label correlations for multi-label classification.
problem Challenging task of predicting multiple targets with label correlations.
method Proposes MPVAE, a novel framework that learns latent embedding spaces and label correlations using a Multivariate Probit model.
result MPVAE outperforms state-of-the-art methods on various application domains and is robust under noisy settings.
Correlated topic modeling has been limited to small model and problem sizes due to their high computational cost and poor scaling. In this paper, we propose a new model which learns compact topic embeddings and captures topic correlations through the closeness between the topic vectors. Our method enables efficient inf…
Paper proposes ICCN to learn correlations between text, audio, and video for multimodal sentiment analysis.
problem Improving multimodal sentiment analysis by learning hidden correlations between text and audio/video features.
method Interaction Canonical Correlation Network (ICCN) using deep canonical correlation analysis (DCCA).
result Empirical results confirm the effectiveness of ICCN in capturing useful information from all three views.
New insights show embedding lengths correlate with semantic properties.
problem Contrastive embedding norms ignore embedding magnitudes but correlate with semantic properties.
method Formal theoretical framework and analysis of optimization dynamics.
result Embedding lengths encode semantic information as a byproduct of training.
Paper analyzes word embedding composition using tensor decomposition.
problem Given vector representations of two words, compute a vector for the entire phrase.
method Generative model with low rank Tucker decomposition of word embedding correlations.
result Word embeddings and a core tensor can be derived from the Tucker decomposition.
Proposes DNN-based speaker embedding correlated with subjective inter-speaker similarity for speech synthesis.
problem Inadequate speaker representation for open speakers not in training data.
method Two training algorithms using inter-speaker similarity matrices: similarity vector embedding and similarity matrix embedding.
result Proposed algorithms learn speaker embedding highly correlated with subjective inter-speaker similarity.
This paper improves sentiment classification by combining text, audio, and video data using DCCA.
problem Improving sentiment classification accuracy using multi-modal data.
method Deep Canonical Correlation Analysis (DCCA) for combining text, audio, and video embeddings.
result One-Step DCCA outperforms current state-of-the-art in multi-modal embedding learning.
Proposes neural model for stock embeddings to capture nuanced asset correlations.
problem Lack of research on modelling financial asset correlations.
method Neural model using historical returns data to learn nuanced relationships.
result Outperforms benchmarks in two real-world financial analytics tasks.
Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. The proposed method is relate…
We propose an approximation algorithm for efficient correlation search in time series data. In our method, we use Fourier transform and neural network to embed time series into a low-dimensional Euclidean space. The given space is learned such that time series correlation can be effectively approximated from Euclidean …
We propose using canonical correlation analysis (CCA) to generate features from sequences of medical billing codes. Applying this novel use of CCA to a database of medical billing codes for patients with diverticulitis, we first demonstrate that the CCA embeddings capture meaningful relationships among the codes. We th…
This work shows cosine similarity is equivalent to Pearson correlation for word vectors, but not all vectors are suitable for cosine.
problem The use of cosine similarity for semantic textual similarity is often taken for granted, despite its limitations.
method Characterized cases where Pearson correlation is unfit and introduced rank correlation as an alternative.
result Pearson correlation is equivalent to cosine similarity for many word vectors but not all, and rank correlation can improve performance.
The study shows how to accurately estimate embedding vectors in high dimensions.
problem How to accurately estimate embedding vectors in high-dimensional spaces.
method A simple probability model and a variant of low-rank approximate message passing (AMP) method.
result The AMP approach enables precise predictions of the accuracy of the estimation in certain high-dimensional limits.
We introduce Gaussian Process Topic Models (GPTMs), a new family of topic models which can leverage a kernel among documents while extracting correlated topics. GPTMs can be considered a systematic generalization of the Correlated Topic Models (CTMs) using ideas from Gaussian Process (GP) based embedding. Since GPTMs w…
PFDL improves deep learning models' OOD generalization by decorrelating feature embeddings.
problem Out-of-distribution generalization in deep learning models.
method PFDL algorithm that optimizes feature decomposition network and image classification model.
result PFDL improves the accuracy of image classification models on OOD datasets.
Proposes a method to learn from multiple views with low-rank embeddings.
problem Learning from multiple views with varying correlations is challenging.
method Multi-view Locality Low-rank Embedding (MvL2E) method that uses low-rank representations and centroid-based scheme.
result MvL2E achieves comparable performance with previous methods on benchmark datasets.
The paper explores how gradient descent trains associative memories, revealing oscillations and convergence issues.
problem Training dynamics of associative memories in overparameterized and underparameterized settings.
method Reduction to particle system dynamics, theory, and experiments.
result Oscillatory transitory regimes and benign loss spikes in overparameterized settings, suboptimal memorization in underparameterized settings.
Study how knots occupy space using topological methods.
problem Understanding how knots occupy a volume of space.
method Statistical analysis of persistent homology features from Vietoris-Rips complexes.
result Existence of correlations between geometric and topological features of knots.
Develops log-Euclidean Lie groups for SPD and correlation matrices.
problem Unifies various log-Euclidean constructions for SPD and correlation matrices.
method Theory and explicit isometries linking different log-Euclidean metrics.
result Explicit log-Euclidean metrics on SPD and correlation matrices.
Two new methods for analyzing repeated measures data using embeddings into Reproducing Kernel Hilbert Spaces.
problem Analyzing complex data structures with multiple features over time.
method Two generalizations of canonical correlation analysis for repeated measures data using embeddings into Reproducing Kernel Hilbert Spaces.
result Consistency rates for transformation and correlation estimators, relaxing common assumptions.
This work explains how maximizing latent correlations across multiple data views helps in identifying shared and private components.
problem Understanding how to identify shared and private components in multiview data.
method An intuitive generative model of multiview data is adopted, and latent correlation maximization is shown to guarantee the extraction of shared components.
result Latent correlation maximization guarantees the extraction of shared components across views and disentangles private information.
Manifold matching works to identify embeddings of multiple disparate data spaces into the same low-dimensional space, where joint inference can be pursued. It is an enabling methodology for fusion and inference from multiple and massive disparate data sources. In this paper we focus on a method called Canonical Correla…
Model predicts community health outcomes from social media language.
problem Linking social media language to community health outcomes.
method Sentence embeddings, regression model, clustering, without additional data.
result Predicts community-level medical outcomes from social media language.
Researchers develop geodesics for a new metric on correlation matrices.
problem Lack of intrinsic tools for statistical analyses of correlation matrices.
method Developed geodesics for the quotient-affine metric on full-rank correlation matrices.
result Provided fundamental Riemannian operations for the quotient-affine metric.
AN2VEC disentangles feature and structural information in social networks.
problem Difficulty in separating feature and structural information in social networks.
method Graph Convolutional Networks (GCN) Variational Autoencoder for disentangled node embeddings.
result AN2VEC captures joint information of structure and features better than unshared information.
Paper proposes AMSRE for multi-view data reduction.
problem Enhance performances of multi-view data tasks.
method Auto-weighted Multi-view Sparse Reconstructive Embedding (AMSRE).
result AMSRE effectively reduces multi-view data dimensions.
Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network clustering, and link prediction. Most, if not all, of the existing works, are ove…
The paper proposes new cross-correlators using Price's Theorem and piecewise-linear decomposition.
problem Optimal method for estimating cross-correlations using finite samples.
method General mathematical framework using Price's Theorem and piecewise-linear decomposition.
result Some cross-correlators based on Huber's loss functions, MP functions, and LSE functions have higher SNR.
This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phra…
CMoS improves time series forecasting with minimal parameters.
problem Efficiently forecasting time series data with limited resources.
method CMoS directly models chunk-wise spatial correlations, using Correlation Mixing and Periodicity Injection techniques.
result CMoS outperforms state-of-the-art models with minimal parameters.
Deep learning models improved sentence similarity in medical records.
problem Improving sentence similarity in electronic medical records.
method Developed models using traditional machine learning and deep learning approaches, pre-trained sentence embeddings on biomedical corpora.
result Ensembled model achieved a Person correlation coefficient of 0.8528.
Method captures shared information across many views robustly.
problem Modeling hundreds of views per event and learning robust embeddings without view knowledge.
method View bootstrapping using multi-view correlation and matrix concentration theory.
result View bootstrapping captures shared information across many views robustly.
Enhances multimodal generation with Normalizing Flows and correlation analysis.
problem Generating coherent cross-modal data from multiple sources.
method Uses Deep Canonical Correlation Analysis for shared information, Normalizing Flows for diversity, and Product of Experts for scalability.
result Improves likelihood, diversity, and coherence in conditional generation.
Unified deep framework for personalized recommendations with uncertainty.
problem Uncertainty in user preferences in recommendation systems.
method Gaussian embeddings, Monte-Carlo sampling, convolutional neural networks.
result Superior performance in recommendation accuracy compared to state-of-the-art models.
A new GNN model predicts stock trends by learning historical and future correlations.
problem Limited improvement in stock trend prediction models due to ignoring future patterns.
method DishFT-GNN framework that trains a teacher and student model to capture historical and future data correlations.
result State-of-the-art performance on real-world datasets.
This is the next step of uncovering the relation between string theory and exotic smooth R^4. Exotic smoothness of R^4 is correlated with D6 brane charges in IIA string theory. We construct wild embeddings of spheres and relate them to a class of topological quantum Dp-branes as well to KK theory. These branes emerge w…
DEMOTE uses neural diffusion-reaction processes to capture temporal dynamics in sparse tensor data.
problem Sparse and temporally associated tensor data with limited structural knowledge.
method Develops a neural diffusion-reaction process to estimate dynamic embeddings for tensor modes.
result Captures both commonalities and personalities in evolving tensor entries.
Proposes BHT-ARIMA for forecasting multiple short time series.
problem Forecasting multiple short time series with mutual correlations.
method Block Hankel tensors, Tucker decomposition, generalized tensor ARIMA.
result Improves forecasting accuracy and reduces computational cost.
Adversarial framework enforces fairness constraints on graph embeddings.
problem Fairness constraints in graph embeddings, especially age and gender.
method Adversarial framework for compositional fairness constraints.
result Framework allows for flexible combinations of fairness constraints.