Method quantifies relation similarity using entity pair distributions.
problem Measuring similarity between relations in knowledge bases.
method Simple neural network parameterizes conditional probability distributions over entity pairs. Sampling-based approximation for similarity computation.
result Approximation correlates with human judgments and detects redundant relations.
Clustering is an underspecified task: there are no universal criteria for what makes a good clustering. This is especially true for relational data, where similarity can be based on the features of individuals, the relationships between them, or a mix of both. Existing methods for relational clustering have strong and …
Researchers solve word2vec's Corpus Replication Task to understand relational word similarities.
problem Understanding how word2vec captures relational similarities in word embeddings.
method Propose a Corpus Replication Task to generate input text for word2vec that outputs specific target relations.
result Demonstrates that word2vec can capture relational similarities in word embeddings.
Proposes a method to capture similarities and covariances between related tasks in multivariate regression.
problem Predicting multiple response variables with shared explanatory variables and capturing within-group similarities.
method Uses multivariate linear mixed models to estimate coefficients and errors, modeling within-group similarities through joint estimation of covariance matrices.
result The proposed MrRCE method outperforms natural competitors and alternative estimators in various model settings.
Proposes a method to measure model parameter similarity for visual tasks.
problem Estimating relations between different visual tasks.
method LPS method using a second-order neural network to align model parameters and learn second-order similarity.
result Extensive experiments validate the effectiveness of the proposed method.
The paper proves recurrence relations for heat kernels on hyperbolic and spherical spaces.
problem Understanding recurrence relations of heat kernels on different space forms.
method Direct proof and computation of recurrence relations for heat kernels on hyperbolic and spherical spaces.
result Computed diagonal of heat kernels for odd dimensional hyperbolic spaces and heat trace asymptotic expansions for odd dimensional spheres.
New method replaces traditional convex integration for solving geometric problems.
problem Constructing solutions with self-similarity properties in geometric embeddings.
method Introducing Kuiper differential relations and a Corrugation Process to replace traditional convex integration.
result Totally real isometric embeddings exhibit self-similarity and can be uniformly expressed.
The paper provides a theoretical framework for learning task similarity in multitask learning.
problem Understanding and leveraging task similarities for improving multitask learning performance.
method The paper derives theoretical bounds on multitask learning generalization error, and proposes a new training algorithm to learn task relation coefficients and neural network parameters.
result The proposed algorithm outperforms baselines and reaffirms the benefits of theoretical insight in algorithm design.
Paper shows similarity learning can lead to strong binary classification performance.
problem How similarity learning can lead to good classification performance.
method Product-type formulation of similarity learning is connected to binary classification through an excess risk bound.
result Similarity learning can directly elicit a decision boundary for binary classification.
The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier. Existing methods typically focus on vectorized data and offer little support for relational data, which additionally describe relationships among instances. In this work we…
Matrix factorization is at the heart of many machine learning algorithms, for example, dimensionality reduction (e.g. kernel PCA) or recommender systems relying on collaborative filtering. Understanding a singular value decomposition (SVD) of a matrix as a neural network optimization problem enables us to decompose lar…
This paper proposes Relational Similarity Machines (RSM): a fast, accurate, and flexible relational learning framework for supervised and semi-supervised learning tasks. Despite the importance of relational learning, most existing methods are hard to adapt to different settings, due to issues with efficiency, scalabili…
Paper proposes a model to integrate diverse drug features for accurate similarity measures.
problem Challenges in integrating heterogeneous, noisy, nonlinear-related drug features.
method Attentive Multi-view Graph Auto-Encoders with flexible design for semi-supervised and unsupervised settings.
result Significant predictive accuracy improvement and better interpretability.
The paper introduces a clustering method for relational matrices using information value.
problem Clustering relational matrices of similarities or dissimilarities.
method Optimizing the value of information through a deterministic annealing process.
result The method automatically determines the number of clusters without prior specification.
Generalizes balanced manifolds to complex spaces, studying their properties and relations.
problem Generalizing balanced manifolds to complex spaces.
method Defined class B and balanced spaces, compared with Kahlerian spaces, and studied properties and relations.
result Properties and relations between balanced spaces and class B are obtained.
Improved S&P stock prediction by integrating related stocks' data.
problem Lack of comprehensive data in stock prediction models.
method Enriched stock data with related stocks, tested five similarity functions, and used co-integration similarity for best results.
result Prediction model on similar stocks had significantly better accuracy and profit.
Deconfounds neural network representation similarity metrics to improve consistency and accuracy.
problem Confounding by population structure in similarity metrics like RSA and CKA.
method Covariate adjustment regression to adjust for confounders.
result Improves detection of semantically similar neural networks and consistency in transfer learning.
This article gives an alternative approach to the self-shrinking and self-expanding solutions of the curve shortening flow, which are related to singularity formation of the mean curvature flow. The motivation for the self-similar solutions arises from natural area preserving rescaling. Further we describe the self-sim…
Defines a similarity measure for classification distributions.
problem Measuring similarity between classification distributions.
method Proposes task similarity, a novel measure quantifying performance of source distributions on target distributions.
result Empirical task similarity correlates with transfer efficiency and semantic similarity of source distributions.
Study isotropy groups for complex orthogonal and skew-symmetric matrices.
problem Understanding isotropy subgroups of orthogonal similarity transformations.
method Analysis of group structure of nonsingular block matrices.
result Group structure of isotropy subgroups related to block Toeplitz matrices.
ClassSim measures similarity between classes using misclassification ratios of trained classifiers.
problem Evaluating similarities between similar classes in real-world datasets.
method ClassSim metric based on misclassification ratios of trained DNNs.
result ClassSim provides better similarities than existing methods for image recognition.
The paper explores log-aesthetic curves under similarity geometry and their relation to Euler's elasticae.
problem Characterizing log-aesthetic curves and their relation to Euler's elasticae.
method The approach involves similarity geometry, variational formulation, and solving the Burgers equation.
result Log-aesthetic curves and their generalization are the similarity geometric analogue of Euler's elasticae.
Simple model classifies traffic tweets from Twitter using word embeddings.
problem Sparsity and curse of dimensionality in bag-of-words representation for traffic tweets.
method Proposes a word embedding-based framework to classify traffic-related tweets from non-traffic ones.
result State-of-the-art test accuracy of 95.9% achieved with a simple model.
The abstract explains how word and relation representations capture semantic meaning.
problem Understanding how word and relation representations capture semantic meaning.
method Theoretical justification and extension of geometric relationships between word embeddings and knowledge graph representations.
result The geometric relationships between word embeddings correspond to semantic relations between words and entities in knowledge graphs.
Model predicts treatment initiation from clinical data using patient-clinician relations.
problem Predicting treatment initiation from clinical time series data considering patient-clinician relations.
method Graph-Augmented Time-Sensitive Model using top eigenvectors of graph Laplacian.
result Relational similarity improves prediction over baselines, e.g., 5% improvement in AUPRC.
Functional Retrofitting improves embedding of unstructured data into knowledge graphs.
problem Combining unstructured data with knowledge graphs that have diverse entities and relations.
method Explicitly models pairwise relations with a variety of penalty functions and allows encoding of relation semantics.
result Significantly outperforms existing retrofitting methods on complex knowledge graphs.
A method for disentangling latent variables using weak supervision based on pairwise similarities.
problem Disentangling latent variables without strong supervision.
method Weak supervision through binary or real-valued similarities, applied within a Variational Autoencoder framework.
result Utilizing weak supervision improves disentanglement performance substantially.
Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually departs from some notion of similarity, comparing two enzymes by looking for correspondences in their sequences, structures or surfaces. For a…
Two private algorithms estimate Jaccard similarity efficiently.
problem Estimating Jaccard similarity while preserving user privacy.
method Extends MinHash with Generalized Randomized Response and Laplace Mechanism.
result Achieves privacy-utility trade-off with theoretical bounds and experiments.
Paper tackles multi-label learning by improving SVR for positive semidefinite metrics.
problem Learning positive semidefinite metrics for multi-label and label distribution learning.
method Proposes two methods to overcome SVR's limitation in learning positive semidefinite metrics.
result Demonstrates new methods achieve favorable performance in multi-label and label distribution learning.
CURE extracts relations without supervision by clustering similar entity pairs.
problem Extracting relations unsupervised without considering sentence correlations.
method CURE uses Encoder-Decoder architecture for self-supervised learning and clustering similar relations.
result CURE outperforms state-of-the-art models on NYT and UNPC datasets.
Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.
problem Learning related but slightly different tasks in an online setting with heterogeneous feedback.
method RobustAgg(ε) algorithm that aggregates rewards from different players. result Achieves instance-dependent regret guarantees and nearly matching lower bounds.
How to price and hedge claims on nontraded assets are becoming increasingly important matters in option pricing theory today. The most common practice to deal with these issues is to use another similar or "closely related" asset or index which is traded, for hedging purposes. Implicitly, traders assume here that the h…
Study 2D viscoelastic equations using Lie group theory.
problem Symmetry classification and reduction of 2D viscoelastic equations.
method Investigation through Lie group theory, including algebra of symmetries and optimal subalgebras.
result Classification of reductions of similarities related to Lie subalgebras.
A new method for measuring document similarity using hierarchical optimal transport.
problem Inability to measure semantic similarities and scalability issues in past document similarity measures.
method Model documents as distributions over topics, topics as distributions over words, solve optimal transport problem on topics.
result Hierarchical optimal transport provides better interpretability and scalability with comparable performance.
Study on transverse Ricci solitons on compact foliated manifolds.
problem Characterizing transverse Ricci solitons on compact foliated manifolds.
method Investigation of self-similar solutions of the transverse Ricci flow, analysis of taut Riemannian foliations.
result Established relations between taut Riemannian foliations and transverse Ricci solitons, found examples of transverse Ricci solitons.
We examine spaces of connected tri-/univalent graphs subject to local relations which are motivated by the theory of Vassiliev invariants. It is shown that the behaviour of ladder-like subgraphs is strongly related to the parity of the number of rungs: there are similar relations for ladders of even and odd lengths, re…
NeuralWarp aligns time-series indices using deep learning for improved similarity.
problem Need for elastic time-series similarity measures.
method Proposes NeuralWarp, a deep learning model for aligning time-series indices.
result NeuralWarp outperforms non-parametric and un-warped deep models.
Similarity algebra extends algebraic structures with quantitative bounds.
problem Exact algebraic structures with strict axioms.
method Framework for approximate algebraic and Lie structures with ε-estimates. result Similarity structures converge to classical algebraic objects as εightarrow0. Financial market dynamics is rigorously studied via the exact generalized Langevin equation. Assuming market Brownian self-similarity, the market return rate memory and autocorrelation functions are derived, which exhibit an oscillatory-decaying behavior with a long-time tail, similar to empirical observations. Individ…
Recently, metric learning and similarity learning have attracted a large amount of interest. Many models and optimisation algorithms have been proposed. However, there is relatively little work on the generalization analysis of such methods. In this paper, we derive novel generalization bounds of metric and similarity …
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
The theory of link-homotopy, introduced by Milnor, is an important part of the knot theory, with Milnor's mu-bar-invariants being the basic set of link-homotopy invariants. Skein relations for knot and link invariants played a crucial role in the recent developments of knot theory. However, while skein relations for Al…
One knows that the large time heat decay exponent on a nilpotent group is given by half the growing rate of the volume of its large balls. This work deals with the similar problem of trying to interpret geometrically the heat decay on (one) forms. We will show how it is (partially) related to the depth of the relations…
This study examines clustering of correlated random variables using k-means and spectral methods.
problem Clustering of correlated random variables.
method Used k-means and spectral algorithms, analyzed different similarity measures.
result Impact of initial points on k-means efficiency was analyzed.
Effectively modelling hidden structures in a network is very practical but theoretically challenging. Existing relational models only involve very limited information, namely the binary directional link data, embedded in a network to learn hidden networking structures. There is other rich and meaningful information (e.…
The paper evaluates different vector space models for text similarity.
problem Measuring semantic text similarity in natural language processing.
method Comparison of TFIDF, topic models, and neural models for patent-to-patent similarity.
result TFIDF performs well for longer, technical texts or finer distinctions.
A new method matches similar regions in non-rigid shapes using spectra of differential operators.
problem Evaluating similarity of non-rigid shapes with partiality.
method Alignment of spectra of differential operators (SI-LBO and regular LBO) on a manifold with multiple metrics.
result Matching spectra outperforms competing methods on standard benchmarks.