GPNNs improve semi-supervised classification on large graphs.
problem Handling large graphs for semi-supervised classification.
method Alternates local and global graph propagation with partitioning.
result GPNNs achieve similar performance with fewer steps than standard GNNs.
A new multilabel classification framework improves ANN search performance.
problem Efficiently finding approximate nearest neighbors in large datasets.
method Formulated ANN search as a multilabel classification problem, using partitioning classifiers.
result Natural classifier leads to strictly improved performance in ANN search.
New classifiers converge under large data, simplifying complex models.
problem Complex predictive models under large datasets.
method Convergence of simultaneous and marginal classifiers under partition exchangeability.
result Asymptotic convergence of classifiers with large data reduces computational complexity.
A novel non-supervised method detects anomalies in multivariate time series.
problem Detecting anomalies in multivariate time series data.
method Partitioning based on clustering of correlation coefficients.
result Significant improvement in anomaly detection performance.
In this article, the logic rule ensembles approach to supervised learning is applied to the unsupervised or semi-supervised clustering. Logic rules which were obtained by combining simple conjunctive rules are used to partition the input space and an ensemble of these rules is used to define a similarity matrix. Simila…
Graphical heuristic reduces and partitions large datasets for faster supervised training.
problem Training large datasets for classification tasks.
method Clustering and information graph construction for dataset reduction and partitioning.
result Significant speed-up in training run-time without compromising prediction accuracy.
This paper proposes a method to learn graph representations by partitioning edges into communities.
problem Graph neural networks ignore how edges are formed, leading to suboptimal representation learning.
method Introduces a generative model to partition edges into community-specific weighted edges, then uses these for GNN-based inference and classification.
result The method learns discriminative representations for both node-level and graph-level classification tasks.
Improved supervised EM learning for shared kernel models with feature space partitioning.
problem Lack of rigour in EM derivation and high computational complexity.
method Detailed derivation of EM for Gaussian shared kernel model, feature space partitioning to reduce complexity.
result Improved performance at reduced complexity achieved.
BELA infers labels for unlabeled data at lower cost.
problem Efficiently labeling large unlabeled datasets.
method Supervised splitting with bias-reduction techniques.
result BELA outperforms existing adaptive labeling strategies.
Proposes LIME-SUP for interpreting complex SML models.
problem Complexity of SML models makes them hard to interpret.
method Fits trees to the fitted response and its derivatives.
result Advantages over KLIME in simulation and real data.
New method improves nearest neighbor search using neural networks and graph partitioning.
problem Efficient nearest neighbor search in high-dimensional spaces.
method Developed a new framework for space partitioning using neural networks and graph partitioning.
result Neural LSH partitions outperform existing methods on standard benchmarks.
SFP extends fuzzy clustering for supervised tasks using labels and entropy regularization.
problem Applying fuzzy clustering to supervised tasks without sacrificing performance.
method Generative model incorporating labels through a surrogate term and entropy regularization.
result SFP outperforms state-of-the-art algorithms on various datasets.
A new method for semi-supervised text classification using layer partitioning.
problem Adapting neural semi-supervised learning to discrete text inputs.
method Decompose neural network into feature extractor F and update layer U for training. Use dropout for systematic noise. result Improves text classification especially on short texts compared to state-of-the-art methods.
Proposes CEC-IB for semi-supervised clustering with side information.
problem Clustering with limited labeled data and partial user information.
method Combines cross-entropy clustering and information bottleneck constraints.
result Outperforms GMM in semi-supervised clustering tasks.
Self-supervised learning improves few-shot classification and segmentation on point clouds.
problem Efficiently learn from limited labeled data in point cloud applications.
method Hierarchical cover-tree partitioning for self-supervised pre-training; restricted to support set for few-shot learning.
result Self-supervised learning significantly improves downstream classification and segmentation accuracy.
A new procedure aggregates models to predict data from multiple clusters.
problem Predicting data from multiple clusters with different underlying models.
method Three-step procedure: clustering, model fitting, and aggregation.
result The method outperforms existing models in various prediction problems.
Online PaLD extends PaLD for semi-supervised online applications.
problem Scalability of unsupervised clustering algorithms for large datasets.
method Adapted partitioned local depth algorithm for online semi-supervised prediction.
result Online PaLD extends cohesion network to new data points efficiently.
Motivated by a geometric problem, we introduce a new non-convex graph partitioning objective where the optimality criterion is given by the sum of the Dirichlet eigenvalues of the partition components. A relaxed formulation is identified and a novel rearrangement algorithm is proposed, which we show is strictly decreas…
Algorithm improves binary classification of biased grouped data.
problem Improving binary classification for biased, grouped data.
method Assumes partition-projected class-conditional invariance across groups and derives a semi-supervised algorithm to learn a group-aware classifier.
result Demonstrates improved area under the ROC curve compared to baselines.
Clustering ensemble is one of the most recent advances in unsupervised learning. It aims to combine the clustering results obtained using different algorithms or from different runs of the same clustering algorithm for the same data set, this is accomplished using on a consensus function, the efficiency and accuracy of…
In this paper, we consider unsupervised partitioning problems, such as clustering, image segmentation, video segmentation and other change-point detection problems. We focus on partitioning problems based explicitly or implicitly on the minimization of Euclidean distortions, which include mean-based change-point detect…
The study analyzes how data augmentation helps isolate content from style in self-supervised learning.
problem Understanding how data augmentation affects the separation of content and style in self-supervised learning.
method Formulated a latent variable model with content and style components, studied identifiability of latent representation, and introduced a dataset to test the theory.
result Sufficient conditions for identifying the invariant content partition in self-supervised learning.
Deep Partition Aggregation defends against poisoning attacks with provable certificates.
problem Adversarial poisoning attacks corrupt classifier test-time behavior.
method Deep Partition Aggregation (DPA) is an ensemble method using hash partitions and base models trained on these partitions.
result DPA can certify >= 50% of test images against over 500 poison image insertions on MNIST, and nine insertions on CIFAR-10.
Spectral clustering is sensitive to how graphs are constructed from data particularly when proximal and imbalanced clusters are present. We show that Ratio-Cut (RCut) or normalized cut (NCut) objectives are not tailored to imbalanced data since they tend to emphasize cut sizes over cut values. We propose a graph partit…
New method for clustering imbalanced clusters.
problem Spectral clustering's sensitivity to imbalanced clusters.
method Proposes a graph partitioning problem with minimum size constraints to handle imbalanced cluster sizes.
result Demonstrates superiority of the proposed method through experiments.
PriDE preserves differential privacy in vertically-partitioned datasets.
problem Privacy issues in distributed machine learning with vertically-partitioned data.
method PriDE uses (ε,δ)-distributed differential privacy to ensure privacy while allowing statistical estimation. result PriDE achieves bounded estimation error compared to non-private methods in distributed settings.
This thesis explores supervised classification methods using Bayesian and exchangeability theories.
problem Assigning objects into predefined classes using training data and auxiliary information.
method Bayesian inductive theories and exchangeabilities (de Finetti and partition exchangeability).
result Optimal classifiers for different scenarios of object features and categories.
DiFF-RF detects point-wise and collective anomalies using random partitioning trees.
problem Detecting anomalies in data, especially collective anomalies.
method Random partitioning binary trees with distance-based leaves and semi-supervised learning.
result DiFF-RF significantly outperforms isolation forest and one-class SVM.
InfoCNF improves conditional image generation by optimizing latent code partitioning and solver error tolerances.
problem Efficiently conditioning CNFs on high-dimensional latent codes for conditional image generation.
method InfoCNF partitions latent space into class-specific and shared codes, and uses gating networks to optimize ODE solver error tolerances.
result InfoCNF improves test accuracy on CIFAR10 while reducing NFEs and maintaining comparable likelihood scores.
Improved biclustering algorithm reduces memory usage and runtime.
problem Efficiently enumerating maximal biclusters in numerical datasets.
method Online partitioning to guide biclustering results.
result RIn-Close_CVC3 reduces memory usage and runtime, handles missing values.
Machine learning uncovers hidden patterns in Calabi-Yau hypersurfaces.
problem Identifying and clustering Calabi-Yau hypersurfaces from weighted-P4s.
method Supervised and unsupervised machine learning techniques.
result High accuracy in predicting topological parameters and identifying hypersurfaces.
A hierarchical segmentation method for images with weak supervision.
problem Weakly supervised image segmentation.
method Flexible hierarchical segmentation considering prior spatial information.
result Enhanced segmentation of regions of interest while preserving important structures.
Bayesian classifiers converge under certain exchangeability conditions with more data.
problem Predictive accuracy of marginal classifiers under varying data conditions.
method Introduced and compared mBpc and sBpc, provided computational scheme for PE sequences, and developed parameter estimation and testing methods.
result mBpc and sBpc converge under PE conditions with increasing data, validating mBpc's use.
New approach uses contrastive learning for better wireless power control.
problem Improving power control in wireless networks.
method A multi-layer perceptron with a contrastive learning backbone and head.
result Significant gains in sum-throughput and sample efficiency over supervised learning.
Efficiently trains deep neural networks with minimal labeled data.
problem Training deep neural networks with limited labeled data in a distributed setting.
method Stochastic regularization over affinity graphs for semi-supervised learning.
result Significant improvement in classification accuracy compared to fully-supervised training.
Cascade-BGNN efficiently learns node representations for large-scale bipartite graphs.
problem Efficiently learning node representations for large-scale bipartite graphs with limited labels.
method Cascade-BGNN uses customized Inter-domain Message Passing (IDMP) and Intra-domain Alignment (IDA) for efficient information aggregation.
result Cascade-BGNN achieves domain-consistent, self-supervised, and efficient node representation learning.
Combines foundation models with weak supervision to improve NLP and video tasks.
problem Leveraging weak supervision with foundation models without labeled data.
method Liger, a combination of foundation model embeddings and weak supervision techniques.
result Liger outperforms existing weak supervision methods by 14.1 points on benchmark NLP and video tasks.
We describe Information Forests, an approach to classification that generalizes Random Forests by replacing the splitting criterion of non-leaf nodes from a discriminative one -- based on the entropy of the label distribution -- to a generative one -- based on maximizing the information divergence between the class-con…
A method to improve clustering explainability using bagging and feature dropout.
problem Lack of explainability in clustering methods.
method Bagging and feature dropout to generate feature importance scores.
result Improved stability and robustness of cluster definition, especially in small-sample or noisy settings.
Proposes a method to improve hierarchical clustering using set-level structural priors.
problem Lack of supervision for non-leaf structure in hierarchical clustering.
method Introduces set-level structural priors for semi-supervised hyperbolic hierarchical clustering.
result Improves label consistency and similarity-based tree quality over baselines.
Parallelizes spectral learning methods for faster computation.
problem Efficiently learning from large datasets in supervised learning.
method Partitioning data into subsets and averaging results from each subset.
result Minimax optimal rates of convergence are preserved under certain conditions.
New method improves self-supervised representation learning using probabilistic modeling and Monte Carlo integration.
problem Improving self-supervised representation learning for multimodal data.
method Discriminative probabilistic modeling with multiple importance sampling (MIS) for robust Monte Carlo integration.
result Proposes a novel non-parametric method for approximating conditional probability densities through convex optimization.
Improved deep learning models with less labelled data and better label quality.
problem High costs and effort in training deep neural networks with label errors.
method Iterative label improvement using confidence-based filtering and dataset partitioning.
result Significant improvement in label quality and model accuracy.
Proposes a differentiable hypergeometric distribution for learning group importance.
problem Learning the sizes of subsets in applications like clustering and weakly-supervised learning.
method Introduces a reparameterizable hypergeometric distribution to model group sizes and learn their relative importance.
result Outperforms previous methods in weakly-supervised learning and clustering.
The paper develops bounds for multiclass semi-supervised learning with penalization.
problem Training multiclass classifiers with limited labeled data.
method Two-step process: clustering and penalized learning.
result Data-dependent generalization error bound with convergence rates.
Cluster analysis methods seek to partition a data set into homogeneous subgroups. It is useful in a wide variety of applications, including document processing and modern genetics. Conventional clustering methods are unsupervised, meaning that there is no outcome variable nor is anything known about the relationship be…
PVAE learns disentangled representations from multimodal data.
problem Learning disentangled representations from multimodal sensory data.
method Partitioned Variational Autoencoder (PVAE) with multimodal generative model and training objectives.
result PVAE achieves over 99% accuracy on both modalities for semantic units.
TACOMA improves cancer biomarker validation by incorporating deep features.
problem Improving accuracy and repeatability in TMA image scoring.
method Incorporating deep learning representations learned through unsupervised clustering and recursive space partitioning.
result Reduced error rate by about 6% on breast cancer TMA images.