DINOSAUR improves retrieval by accounting for embedding uncertainty in recommender systems.
problem Retrieval bias towards popular items due to noisy embeddings.
method Samples multiple embeddings per item and queries with sampled embeddings to account for uncertainty.
result Improves coverage of long-tail niche content without sacrificing recall.
This paper improves t-SNE using Isolation kernel for better data representation and efficiency.
problem Misrepresentation of data structures and high computational cost in t-SNE.
method Replacing Gaussian kernel with Isolation kernel in t-SNE.
result Isolation kernel improves t-SNE's accuracy and efficiency without sacrificing quality.
We study the approximate nearest neighbour method for cost-sensitive classification on low-dimensional manifolds embedded within a high-dimensional feature space. We determine the minimax learning rates for distributions on a smooth manifold, in a cost-sensitive setting. This generalises a classic result of Audibert an…
In this paper we propose and explore the k-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates. We focus on a setting where the covariates are supported on a metric space of low intrinsic dimension, such as a manifold embedded within a high dimensional ambient feature space. The algorithm is concept…
New algorithm improves topological stability in non-linear dimensionality reduction.
problem Topological instability in choosing nearest neighbors in Isomap.
method Uses point and its two nearest neighbors to find subspace and orthogonal complement, then adds new points based on distance and angle.
result Improves topological stability and reduces short-circuit errors.
RR-GCN uses random transformations instead of learned weights for node embeddings.
problem Learning node embeddings in KGs.
method Random Relational Graph Convolutional Network (RR-GCN) with untrained parameters.
result RR-GCN can compete with fully trained R-GCNs in node classification and link prediction.
Validates network bootstraps for uncertainty quantification in network visualisation.
problem Quantifying uncertainty in network embeddings when only a single observation is available.
method Statistical indistinguishable embeddings using k-nearest neighbour smoothing, validated by an exchangeable network test.
result Proposes a principled, distribution-free network bootstrap that passes the exchangeable network test.
A review of nearest neighbour classifiers, focusing on similarity measures and computational efficiency.
problem Improving the performance of nearest neighbour classifiers.
method Explains mechanisms for assessing similarity (distance), identifying nearest neighbours, and reducing data dimensionality.
result Added new sections on time-series similarity measures, retrieval speed-up, and intrinsic dimensionality.
Proposes a new k-NN algorithm to improve classification accuracy by removing noise and pseudo-neighbours.
problem Noise and pseudo-neighbours in large-scale databases affect k-NN performance.
method Introduces a weighted mutual k-Nearest Neighbour algorithm to detect and remove noise, and minimize distant neighbours' influence.
result The proposed algorithm provides comparative better results compared to standard k-NN.
New methods for visualizing multi-view data improve clustering accuracy.
problem Visualizing multi-view data for better understanding of samples.
method Extensions of manifold learning methods (t-SNE, LLE, ISOMAP) for multi-view data.
result Improved clustering accuracy of multi-view data.
New algorithm reduces regret in contextual bandits with many near-boundary contexts.
problem High regret in contextual bandits with many near-boundary contexts.
method Hierarchical nearest neighbour approach, holding out contexts for computation.
result Eradicates high regret in adversarial contextual bandits.
New method estimates gradients accurately with sharp bounds.
problem Accurate gradient estimation in regression problems.
method Nearest-neighbor based pointwise estimate of gradients.
result Sharp nonasymptotic bounds for gradient estimation.
Probabilistic k-nearest neighbour (PKNN) classification has been introduced to improve the performance of original k-nearest neighbour (KNN) classification algorithm by explicitly modelling uncertainty in the classification of each feature vector. However, an issue common to both KNN and PKNN is to select the optimal n…
T-distributed stochastic neighbour embedding (t-SNE) is a widely used data visualisation technique. It differs from its predecessor SNE by the low-dimensional similarity kernel: the Gaussian kernel was replaced by the heavy-tailed Cauchy kernel, solving the "crowding problem" of SNE. Here, we develop an efficient imple…
A new adaptive kNN classifier outperforms Random Forests.
problem Improving classification accuracy using nearest neighbors.
method Finding discriminant subspaces for efficient nearest neighbor classification, leveraging bagging for diversity.
result The proposed method outperforms Random Forests and other nearest neighbors ensembles.
DBSCAN clustering improved by using nearest neighbour-induced Isolation Similarity.
problem Improving clustering performance of DBSCAN.
method Proposed nearest neighbour method to implement Isolation Similarity.
result DBSCAN clustering performance surpassed by DP algorithm.
A hybrid K-NN and SVM technique improves classification accuracy.
problem Improving classification accuracy in pattern recognition.
method Discriminative nearest neighbour classification combined with SVM.
result The hybrid technique outperforms state-of-the-art methods.
A scalable GPVAE method using local adjacencies to approximate GP inference.
problem Scalability issues in exact GP inference for large-scale GPVAEs.
method Neighbour-driven approximation strategy that confines computations to nearest neighbours.
result Outperforms other GPVAE variants in predictive performance and computational efficiency.
We study algebraic properties of matrices whose rows are mutual neighbours, and are also neigbours of 0 ("neighbour" in the sense of a certain nilpotency condition). The intended application is in synthetic differential geometry. For a square matrix of this kind, the product of the diagonal entries equals the determina…
The three-state agent-based 2D model of financial markets in the version proposed by Giulia Iori in 2002 has been herein extended. We have introduced the increase of herding behaviour by modelling the altering trust of an agent in his nearest neighbours. The trust increases if the neighbour has foreseen the price chang…
Optimizes one-class classification methods for better performance.
problem Improving one-class classification accuracy through hyperparameter optimization.
method Hyperparameter optimization for five one-class classification methods (SVM, NND, LNND, LOF, ALP) using various datasets.
result ALP and SVM perform best after hyperparameter optimization, with ALP being more efficient.
Intuitive clustering algorithm balances cluster size and cohesion.
problem Cluster definition and selection in data analysis.
method Nearest neighbours equilibrium condition for clustering.
result High-quality clustering solutions compared to benchmarks.
A framework for flagging content with limited data.
problem Content flagging with scarce target-language data.
method Nearest-neighbor architecture using Transformer representations.
result Significant performance improvements over prior work.
Novel estimator reduces diffusion model variance.
problem High variance in score function estimation for diffusion models.
method Uses nearest neighbour samples to estimate the score function.
result Significant decrease in variance, leading to improved model performance.
Proposes a block-based model for attributed network embedding.
problem Handles both assortative and disassortative networks.
method Assigns nodes to blocks based on similar linkage patterns, using neural networks to preserve attribute information.
result Consistently outperforms state-of-the-art methods on disassortative networks.
Auto insurers improve risk assessment using t-SNE.
problem Accurate risk estimation for auto insurance policyholders.
method Combining neural network with t-SNE for dimensionality reduction.
result Visual representation of risk as a 2D surface, revealing high vs low risk policyholders.
Novel method for learning Gaussian graphical models from paired data.
problem Learning Gaussian graphical models for dependent groups.
method Introducing twin order to explore the search space more efficiently.
result The twin order makes the model space a distributive lattice, leading to more efficient model exploration.
K-Nearest Neighbours (k-NN) is a popular classification and regression algorithm, yet one of its main limitations is the difficulty in choosing the number of neighbours. We present a Bayesian algorithm to compute the posterior probability distribution for k given a target point within a data-set, efficiently and withou…
There is an increasing body of evidence suggesting that exact nearest neighbour search in high-dimensional spaces is affected by the curse of dimensionality at a fundamental level. Does it necessarily mean that the same is true for k nearest neighbours based learning algorithms such as the k-NN classifier? We analyse t…
New graph representation learning network improves scalability and feature integration.
problem Scalability and feature integration in graph neural networks for large, dense graphs.
method Adaptive sampling of neighbours based on weighted multi-step transition probabilities.
result Comparable or better results on various graph benchmarks.
Study classifies liability insurance policies using machine learning.
problem Classifying liability insurance policies with or without claims.
method Used machine learning models like nearest neighbour and logistic regression on Actuarial Challenge dataset.
result Models accurately classified policies into claims and non-claims groups.
Develops a theoretical framework for scalable Gaussian Process regression methods.
problem Limited scalability of Gaussian Process regression for large datasets.
method Introduces and analyzes Nearest Neighbour Gaussian Process (NNGP) and scalable GPnn methods.
result Derives almost sure pointwise limits for predictive criteria and proves risk minimax rates.
Unified framework evaluates different nearest neighbor classification methods.
problem Evaluating and comparing classical, fuzzy, and fuzzy rough nearest neighbor classification methods.
method Standardized nearest neighbor weighting with kernel functions applied to distance and/or rank values of nearest neighbors.
result NN, FNN, and FRNN perform best with Boscovich distance, and NN and FRNN perform best with specific combinations of weights and scaling measures.
Novel model selection method outperforms current state-of-the-art in high-dimensional graphical models.
problem Accurate model selection in high-dimensional graphical models.
method Graphical Neighbour Information (GNI) criterion.
result Demonstrates oracle performance in high-dimensional model selection, outperforming current methods.
Piecewise flat approximations for curvature in Euclidean and non-Euclidean spaces.
problem Approximating local extrinsic curvature on discrete manifolds.
method Constructing discrete curvature forms on piecewise flat manifolds, using weighted sums of hinge angles.
result Converges to smooth curvature values as mesh refinement occurs, favorably comparing with other discrete approaches.
Generative LLE modifies LLE to generate stochastic embeddings.
problem Nonlinear dimensionality reduction and manifold learning.
method Generative LLE modifies LLE by using stochastic linear reconstruction.
result Generative LLE can generate various LLE embeddings stochastically.
Fractionally integrated generalized autoregressive conditional heteroskedasticity (FIGARCH) arises in modeling of financial time series. FIGARCH is essentially governed by a system of nonlinear stochastic difference equations ut = zt $(1-\sum\limits_{j=1}^q β_j L^j)σ_{t}^2 = ω+(1-\sum\limits_{j=1}^q β_j L^j -…
Estimates multiple means in high dimensions using convex combinations.
problem Estimating multiple multi-dimensional means from samples.
method Convex combinations of empirical means with data-dependent weights.
result Our methods asymptotically approach oracle (minimax) improvement.
Study ruin probabilities in risk processes on stochastic networks.
problem Ruin probabilities in risk processes on stochastic networks.
method Classification of agents by types, Poisson process for loss propagation, explicit ruin probabilities for infinite network size.
result Explicit ruin probabilities for agents of any type in infinite network size.
Framework uses machine learning to distinguish major COVID-19 variants.
problem Discriminate and visualize associations between major COVID-19 variants based on genome sequences.
method Unsupervised machine learning methods, including k-mer analysis, PCA, t-SNE, UMAP, and agglomerative hierarchical clustering.
result Framework effectively distinguishes between major variants and identifies emerging variants.
We give a simple combinatoric proof of an exponential upper bound on the number of distinct 3-manifolds that can be constructed by successively identifying nearest neighbour pairs of triangles in the boundary of a simplicial 3-ball and show that all closed simplicial manifolds that can be constructed in this manner are…
Adaptive framework improves nonparametric dimensionality reduction.
problem Optimal hyper-parameter tuning for nonparametric dimensionality reduction.
method Adaptive framework using intrinsic dimension estimator and optimal local neighbourhood sizes.
result Significant improvements in various learning tasks through better low-dimensional visualizations.
The classification of time series data is a well-studied problem with numerous practical applications, such as medical diagnosis and speech recognition. A popular and effective approach is to classify new time series in the same way as their nearest neighbours, whereby proximity is defined using Dynamic Time Warping (D…
For graphs generated from stochastic blockmodels, adjacency spectral embedding is asymptotically consistent. Further, adjacency spectral embedding composed with universally consistent classifiers is universally consistent to achieve the Bayes error. However when the graph contains private or sensitive information, trea…
In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters. Tikhonov regularization, graph-based regularization, and hard parameter sharing are approaches that introduce explicit biases into training in a hope to reduce statistical complexity. Alternatively, we propo…
Paper proposes MS-k-NN for improved convergence rate in k-NN classification.
problem Improving convergence rate of k-NN classification methods.
method Proposes MS-k-NN that extrapolates unweighted k-NN estimators to k=0.
result MS-k-NN achieves improved convergence rate under certain conditions.
We developed a convolution neural network (CNN) on semi-regular triangulated meshes whose vertices have 6 neighbours. The key blocks of the proposed CNN, including convolution and down-sampling, are directly defined in a vertex domain. By exploiting the ordering property of semi-regular meshes, the convolution is defin…
Neural network learns from higher-order connections in molecules.
problem Graph neural networks fail to account for local and hidden structures in graphs.
method Developed a neural network that can pass messages and aggregate information across higher-order paths.
result The model improves molecular property prediction.