New multitask algorithm separates rare from frequent protein functions.
problem Challenging automated protein function prediction with unbalanced data.
method Uses dissimilarity information to separate rare class labels, unlike similarity-based approaches.
result Multitask label propagation algorithm performs best with dissimilarity matrix.
BERT improved for propaganda detection with imbalanced, dissimilar data.
problem BERT struggles with dissimilar imbalanced datasets in propaganda detection.
method Cost-sensitive BERT with dissimilarity measure for imbalanced, dissimilar datasets.
result Achieved second-highest score on sentence-level propaganda classification.
Random Forest proximity measures for multi-view classification.
problem Combining multiple heterogeneous data views for classification.
method Building dissimilarity representations for each view, fusing them dynamically.
result Dynamic View Selection improves multi-view classification performance.
New RF dissimilarity measures improve multi-view learning accuracy.
problem Improving multi-view learning accuracy in HDLSS problems.
method Modified Random Forest proximity measures for HDLSS multi-view classification.
result Second method significantly more accurate than other state-of-the-art methods.
Sparse routing networks with co-training prevent catastrophic forgetting in continual learning.
problem Catastrophic forgetting in neural networks trained on a sequence of tasks.
method Sparse routing networks with co-training to minimize interference between dissimilar tasks.
result Sparse routing networks with co-training outperform densely connected networks on benchmarks.
Improved detection of brain tumours in MRIs using latent space dissimilarities.
problem Detecting tumours in brain MRIs using unsupervised learning.
method Slice-wise semi-supervised method based on dissimilarity between latent representations of images and their reconstructions.
result Improved detection results with higher resolution images and better reconstructions.
Meta-learning framework uses task similarity through nonparametric kernel regression.
problem Limited tasks and outliers/dissimilar tasks hinder meta-learning performance.
method Nonparametric kernel regression to quantify and use task similarity.
result Meta-learning algorithm outperforms existing methods in task-limited settings.
New properties for density-based dissimilarity measures in hybrid clustering are proposed and evaluated.
problem Choosing the right dissimilarity measure for hybrid clustering.
method Six data-independent properties for density-based dissimilarity measures are proposed and evaluated.
result A new dissimilarity measure based on Kullback-Leibler information is introduced and shown to satisfy all proposed properties.
sCSC clusters data without prior assumptions, revealing natural groupings.
problem Clustering data without prior knowledge of its structure.
method sCSC performs binary splittings maximizing dissimilarity, producing a binary tree.
result Clusters emerge naturally from the binary tree, revealing data structure.
Improves cross-modal retrieval by integrating unlabeled data.
problem Lack of semantic similarity constraints and unlabeled data in cross-modal retrieval.
method Integrates quadruplet ranking loss and semi-supervised contrastive loss in a multi-task learning architecture.
result Boosts cross-modal retrieval accuracy by exploiting unlabeled data.
DMAE uses neural networks to cluster data with flexible dissimilarity functions.
problem Clustering data with complex dissimilarity functions.
method Integrates a dissimilarity mixture model into deep learning architectures.
result DMAE achieves competitive clustering accuracy compared to other methods.
Extends RSP model with net flow and capacity constraints for better network analysis.
problem Improving shortest path models with net flows and capacity constraints.
method Developed net flow RSP model and introduced capacity constraints. Proposed algorithms for computing expected routing costs and solving constrained problems using Lagrangian duality.
result Net flow RSP dissimilarity measure is competitive with state-of-the-art dissimilarities.
New method clusters stationary stochastic processes using covariance-based dissimilarity.
problem Clustering wide-sense stationary ergodic stochastic processes.
method Covariance-based dissimilarity measure with consistent algorithms for offline and online clustering.
result Asymptotically consistent algorithms for efficient clustering.
New RDPC dissimilarity measure improves time series clustering.
problem Improving time series clustering methods for diverse data.
method Combining weighted Pearson correlation with largest element-wise differences.
result RDPC outperforms existing methods in complex datasets.
E2Tree explains random forest models in regression tasks.
problem Lack of transparency in random forest models.
method E2Tree extends random forest to regression by explaining model predictions through graphical representation and dissimilarity measures.
result E2Tree provides a transparent explanation of random forest models in regression tasks.
mp-LSH shares hash codes for multiple dissimilarities.
problem Hash codes depend on dissimilarity, limiting query-time adjustments.
method mp-LSH shares hash codes for L2, cosine, inner product, and weighted sums.
result mp-LSH supports user-adjustable weights and feature importance.
Proposes LOD to measure latent vs observed variables dissimilarity.
problem Quantitatively assessing relationships between latent and observed variables.
method Proposes latent-observed dissimilarity (LOD) and defines four generative model types.
result LOD effectively captures differences between models and reflects higher layer learning capability.
The paper proposes scalable methods for selecting prototypes from large dissimilarity datasets.
problem Selecting good prototypes from large dissimilarity datasets.
method Genetic algorithms, dissimilarity-based hashing, unsupervised and supervised criteria.
result The methods select good prototypes efficiently from large datasets.
The paper develops methods for clustering directed dissimilarity networks.
problem Clustering directed dissimilarity networks.
method Admissible methods based on axioms of value and transformation.
result Unique admissible clustering method exists when modifying the axiom of value.
Optimizes edge coloring in graph bundling for better edge differentiation.
problem Difficulty in identifying origins and destinations of individual edges in strongly bundled graphs.
method Optimizes edge coloring based on pairwise edge strength and origin-destination dissimilarity, solving a nonlinear optimization problem.
result Peacock bundles enhance graph layout comprehensibility with edge differentiation.
DID measures similarity invariant to diffeomorphisms.
problem Measuring similarity invariance to diffeomorphisms.
method DID measures similarity as the solution to an optimization problem in a Reproducing Kernel Hilbert Space.
result DID is invariant to diffeomorphisms and can be efficiently approximated.
Paper introduces a new method for learning with distributions using dissimilarity measures.
problem Learning with probability distributions using dissimilarity measures.
method Introduces embeddings based on dissimilarity of distributions to templates, extending similarity theory to population distributions.
result Proves that dissimilarity theory holds for empirical distributions and shows better performance of Wasserstein distance embedding.
New dissimilarity measures enhance affinity propagation for complex network clustering.
problem Improving community detection in complex networks using affinity propagation.
method Leverage network latent geometry to design dissimilarity matrices.
result Affinity propagation outperforms state-of-the-art methods in community detection.
Improves Gower's similarity for mixed-type variables with automatic weighting.
problem Handling missing values and unbalanced variable contributions in Gower's similarity for mixed-type data.
method Automatic weighting scheme minimizing differences in correlation between contributing dissimilarities and weighted Gower's dissimilarity.
result Improved performance in classification and imputation of missing values.
Debiased contrastive learning improves representation learning by correcting for same-label sampling.
problem Sampling negative examples from truly different labels improves performance in self-supervised representation learning.
method Developed a debiased contrastive objective that corrects for the sampling of same-label datapoints without true labels.
result The proposed debiased contrastive objective consistently outperforms state-of-the-art methods across vision, language, and reinforcement learning benchmarks.
A method for classification using pairwise similarities and unlabeled data.
problem Handling pairwise similarities and unlabeled data for classification.
method Empirical risk minimization approach to create an unbiased risk estimator.
result Derives an unbiased risk estimator for handling both similarities and unlabeled data.
FPI methods compute barycenters of Gaussian sets for various dissimilarity measures.
problem Efficiently compute barycenters of Gaussian sets for multiple dissimilarity measures.
method Fixed-Point Iterations (FPI) for several dissimilarity measures.
result FPI provides a useful toolbox for fusion/reduction of Gaussian sets.
Paper proposes a new efficient transport-based dissimilarity measure for time series classification.
problem Classifying time series with warping distortions.
method Defining a problem statement, proposing an Optimal Transport-based dissimilarity measure.
result The proposed method can solve the time series classification problem with reduced computational cost.
ClustGeo uses Ward-like clustering with spatial constraints in R.
problem Hierarchical clustering with spatial/geographical constraints.
method Ward-like hierarchical clustering algorithm with two dissimilarity matrices and a mixing parameter.
result Determines optimal spatial contiguity without sacrificing variable quality.
A new method for functional data clustering using varying smoothing parameters.
problem Determining dissimilarity between subjects in functional data.
method Measuring dissimilarity based on varying curve estimates with commutation of smoothing parameters pair-by-pair.
result The method effectively clusters subjects and has practical advantages.
Paper introduces a method for supervised hierarchical clustering with Exponential Linkage.
problem Discrepancy between training and clustering objectives in supervised clustering.
method Tightly couples supervised training of dissimilarity function with hierarchical clustering, using Exponential Linkage.
result Joint training procedure consistently matches or outperforms other methods, improving dendrogram purity by up to 8 points.
Optimal task order improves continual learning performance.
problem Challenges in neural networks learning multiple tasks in sequence.
method Linear teacher-student model with latent factors, derived analytical expression.
result Two principles for optimal task order: least representative first and dissimilar adjacent tasks.
The one-class classification problem is a well-known research endeavor in pattern recognition. The problem is also known under different names, such as outlier and novelty/anomaly detection. The core of the problem consists in modeling and recognizing patterns belonging only to a so-called target class. All other patte…
A new method for visualizing group dissimilarity using Likelihood Ratio Test.
problem Explaining group differences when null hypothesis is rejected.
method The Merging Path Plot and factorMerger package.
result Visualization of group dissimilarity using Likelihood Ratio Test.
Method reveals dissimilarity in alloys' Curie temperatures.
problem Tackles the dissimilarity between rare-earth transition metal binary alloys.
method Ensemble learning with Kernel ridge regression.
result Reveals meaningful relations between alloys' structure and Curie temperature.
There have lately been several suggestions for parametrized distances on a graph that generalize the shortest path distance and the commute time or resistance distance. The need for developing such distances has risen from the observation that the above-mentioned common distances in many situations fail to take into ac…
Multiple instance learning (MIL) is concerned with learning from sets (bags) of objects (instances), where the individual instance labels are ambiguous. In this setting, supervised learning cannot be applied directly. Often, specialized MIL methods learn by making additional assumptions about the relationship of the ba…
We introduce in this paper a new way of optimizing the natural extension of the quantization error using in k-means clustering to dissimilarity data. The proposed method is based on hierarchical clustering analysis combined with multi-level heuristic refinement. The method is computationally efficient and achieves bett…
We consider the problem of identifying patterns in a data set that exhibit anomalous behavior, often referred to as anomaly detection. Similarity-based anomaly detection algorithms detect abnormally large amounts of similarity or dissimilarity, e.g.~as measured by nearest neighbor Euclidean distances between a test sam…
A new weighted dissimilarity measure reduces positioning errors in feature-based systems.
problem Reducing errors in feature-based positioning systems, especially in areas with high variability.
method Iterative scheme using location-dependent standard deviations as weights.
result Maximum radial positioning error reduced by 40% using the weighted dissimilarity measure.
FedProx algorithm improved for non-smooth and heterogeneous data.
problem Theoretical understanding of FedProx for non-convex federated optimization.
method Local dissimilarity invariant convergence theory through algorithmic stability.
result Convergence guarantees for non-smooth FL problems and minibatch size.
Method identifies regions of maximum dissimilarity in stochastic processes.
problem Comparing local characteristics of two random processes to find periods of maximum dissimilarity.
method Bayesian inference with integrated nested Laplace approximation for stochastic processes.
result Identifies regions of maximum dissimilarity with a certain volume.
Two new algorithms select matrix rows and columns to preserve distances.
problem Preserving distances in large matrix visualizations.
method Selects rows and columns to preserve distances.
result Preserves distances as closely as possible.
In numerous applicative contexts, data are too rich and too complex to be represented by numerical vectors. A general approach to extend machine learning and data mining techniques to such data is to really on a dissimilarity or on a kernel that measures how different or similar two objects are. This approach has been …
Topolow embeds dissimilarity data into Euclidean space robustly against non-metricity and sparsity.
problem Embedding dissimilarity data into Euclidean space when dissimilarities are non-metric or sparse.
method Topolow uses a physics-inspired, gradient-free optimization framework to maximize likelihood under a Laplace error model.
result Topolow outperforms standard MDS methods in reconstructing sparse and non-Euclidean data.
A new method uses online mixtures of tasks to improve meta-learning efficiency.
problem Difficulty in meta-learning when tasks are dissimilar or change over time.
method Proposes a Dirichlet process mixture of hierarchical Bayesian models for task-dependent hyperparameter selection.
result Better handles latent distribution shift on evolving few-shot learning benchmarks.
New method assesses data clusterability using ultrametricity.
problem Determining if large datasets are efficiently clusterable.
method Proposes a novel ultrametric-based approach to evaluate clusterability via matrix product.
result Demonstrates the generation of sub-dominant ultrametric from dissimilarity space.
The paper analyzes phase transitions in transfer learning for perceptrons.
problem Understanding when transfer learning from a source task to a target task is beneficial.
method Theoretical analysis of a pair of related perceptron learning tasks.
result Reveals a phase transition from negative to positive transfer as task similarity changes.