New algorithm IAC recovers hidden communities in labeled SBM with optimal performance.
problem Recovering hidden communities in Labeled Stochastic Block Model with varying cluster sizes.
method IAC (Instance-Adaptive Clustering) algorithm, consisting of spectral clustering and iterative likelihood-based improvements.
result IAC achieves optimal performance matching instance-specific lower bounds in expectation and with high probability.
Sensors which use electromagnetic induction (EMI) to excite a response in conducting bodies have long been investigated for subsurface explosive hazard detection. In particular, EMI sensors have been used to discriminate between different types of objects, and to detect objects with low metal content. One successful, p…
Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test set. We hypothesize that this poor generalization is a consequence of adversarial …
Calibrated PRMs improve inference efficiency for LLMs by dynamically adjusting compute budgets.
problem Poor calibration of PRMs leads to overestimation of success probabilities in partial reasoning steps.
method Quantile regression for calibration, instance-adaptive scaling (IAS) framework.
result Calibrated PRMs reduce inference costs while maintaining accuracy, especially on confident problems.
This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.
problem Challenges in providing meaningful uncertainty quantification for semantic information in disentangled latent spaces.
method Uses quantile regression to output heuristic uncertainty intervals, calibrates these intervals to contain true latent values, and propagates them through the generator.
result Reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in image super-resolution and image completion.
In remote sensing, it is often challenging to acquire or collect a large dataset that is accurately labeled. This difficulty is usually due to several issues, including but not limited to the study site's spatial area and accessibility, errors in the global positioning system (GPS), and mixed pixels caused by an image'…
A method predicts posterior PCs for faster uncertainty quantification in imaging.
problem Uncertainty visualization in image restoration models is limited by per-pixel variances.
method Neural Posterior Principal Components (NPPC) method for predicting PCs in a single forward pass.
result Orders of magnitude faster uncertainty quantification compared to posterior samplers.
AM-PPI uses multiple predictors to reduce label cost in healthcare AI.
problem Reduces label cost in post-deployment monitoring of healthcare AI.
method Combines model predictions with a small labeled sample, routing each instance to a cost-appropriate subset of predictors.
result Produces narrower confidence intervals than single-predictor methods.
Model financial network dynamics to avoid systemic risk.
problem Avoid systemic risk in financial networks.
method Model financial network as random liability graph, agents adapt strategies based on learning, analyze using ODE.
result Emerging strategies converge to evolutionary stable strategies (all risky or all less risky agents).
The paper proposes a method to improve random forest classification accuracy by weighting trees based on their decision path reliability.
problem Random forests' uniform voting fails to correct errors in regions where incorrect tree representations outnumber correct ones.
method The paper introduces using the structural pattern of each tree's decision path as an instance-adaptive reliability signal to identify and weight more reliable trees.
result Using the proposed method yields a statistically significant accuracy improvement over RF on 36 binary classification benchmarks.
Convex clustering can only learn convex clusters, with significant gaps between clusters.
problem Understanding the limitations and capabilities of convex clustering.
method Analyzing convex clustering solutions, proving properties, and characterizing clusters.
result Convex clustering can only learn convex clusters with significant gaps between clusters.
Proposes a new clustering method based on expectiles for non-spherical clusters.
problem Inability of K-means to handle non-spherical clusters. method Uses expectiles to define cluster centers and searches for clusters via a greedy algorithm.
result Outperforms K-means and spectral clustering on asymmetric shaped clusters. CCMM efficiently solves large-scale convex clustering problems.
problem Scalability and hierarchical structure in convex clustering.
method Majorization-minimization algorithm with cluster fusions and efficient updating.
result CCMM achieves efficient solutions for large datasets.
Discussing issues in robust clustering, especially with Gaussian models.
problem Handling outliers and ambiguity in clustering groups.
method Focus on Gaussian mixture model, examining formal definitions, interactions, and tuning decisions.
result Outliers can confuse clustering groups and existing stability measures fail with them.
New indices for determining cluster compactness and separability.
problem Challenges in identifying true clusters in data sets.
method Developed absolute cluster indices to measure compactness and separability.
result Demonstrated improved performance compared to existing indices.
Mode clustering is a nonparametric method for clustering that defines clusters using the basins of attraction of a density estimator's modes. We provide several enhancements to mode clustering: (i) a soft variant of cluster assignment, (ii) a measure of connectivity between clusters, (iii) a technique for choosing the …
Clustering is an essential data mining tool that aims to discover inherent cluster structure in data. For most applications, applying clustering is only appropriate when cluster structure is present. As such, the study of clusterability, which evaluates whether data possesses such structure, is an integral part of clus…
In this paper, a similarity-driven cluster merging method is proposed for unsuper-vised fuzzy clustering. The cluster merging method is used to resolve the problem of cluster validation. Starting with an overspecified number of clusters in the data, pairs of similar clusters are merged based on the proposed similarity-…
The paper improves on existing algorithms for minimizing different types of regret in online learning.
problem Minimizing external, internal, and swap regret in online learning with multiple experts.
method Develops a single algorithm using φ-regret minimization and Haar-wavelet-inspired matrix features to achieve optimal bounds in various scenarios.
result Achieves optimal bounds for external, internal, and swap regrets in different expert scenarios.
Clustering ensemble, or consensus clustering, has emerged as a powerful tool for improving both the robustness and the stability of results from individual clustering methods. Weighted clustering ensemble arises naturally from clustering ensemble. One of the arguments for weighted clustering ensemble is that elements (…
In many practical applications of clustering, the objects to be clustered evolve over time, and a clustering result is desired at each time step. In such applications, evolutionary clustering typically outperforms traditional static clustering by producing clustering results that reflect long-term trends while being ro…
Study examines how cluster number affects short-text clustering, introducing a stability metric.
problem Challenges in finding meaningful clusters in short-text data.
method Introduces a stability metric to determine cluster robustness and visualizes cluster subdivisions.
result Choosing a cluster number involves balancing informativeness and complexity, not seeking a single 'optimal' solution.
Convex clustering, a convex relaxation of k-means clustering and hierarchical clustering, has drawn recent attentions since it nicely addresses the instability issue of traditional nonconvex clustering methods. Although its computational and statistical properties have been recently studied, the performance of convex c…
Cluster LOCO: A model-agnostic feature importance score for interpreting cluster outputs
problem Interpreting and auditing cluster outputs
method Cluster LOCO (Leave-One-Covariate-Out)
result More reliably recovers informative features than existing methods
Clustering is a central approach for unsupervised learning. After clustering is applied, the most fundamental analysis is to quantitatively compare clusterings. Such comparisons are crucial for the evaluation of clustering methods as well as other tasks such as consensus clustering. It is often argued that, in order to…
Clustering is one of the most universal approaches for understanding complex data. A pivotal aspect of clustering analysis is quantitatively comparing clusterings; clustering comparison is the basis for many tasks such as clustering evaluation, consensus clustering, and tracking the temporal evolution of clusters. In p…
A new distributed clustering framework using distributional kernel.
problem Clustering in distributed networks with arbitrary shapes, sizes, and densities.
method Distributed Clustering based on Distributional Kernel (KDC) using similarity of distributions.
result KDC guarantees equivalent clustering outcomes to centralized methods, reduces runtime, and discovers arbitrary clusters.
Skeleton clustering detects clusters in high-dimensional data without needing prototypes.
problem Detecting clusters in high-dimensional data with irregular shapes.
method Skeleton clustering combines prototype methods, density-based clustering, and hierarchical clustering using surrogate density measures.
result Skeleton clustering reliably detects clusters in multivariate and high-dimensional data.
EAP clusters evolving data, promoting temporal smoothness and automatic cluster tracking.
problem Clustering time-evolving data with temporal smoothness and automatic cluster identification.
method Evolutionary Affinity Propagation (EAP) on a factor graph exchanging messages between adjacent data snapshots.
result EAP clusters data with temporal smoothness and automatically tracks clusters, outperforming existing methods.
Determining the number of clusters present in a dataset is an important problem in cluster analysis. Conventional clustering techniques generally assume this parameter to be provided up front. %user supplied. %Recently, robustness of any given clustering algorithm is analyzed to measure cluster stability/instability wh…
Typically clustering algorithms provide clustering solutions with prespecified number of clusters. The lack of a priori knowledge on the true number of underlying clusters in the dataset makes it important to have a metric to compare the clustering solutions with different number of clusters. This article quantifies a …
A novel approach ODAR detects outliers for clustering.
problem Outliers interfere with clustering algorithms, leading to unreliable results.
method Feature transformation to separate outliers and normal objects into distinct clusters.
result ODAR improves clustering accuracy on 7 out of 10 datasets.
Exact cluster recovery with same-cluster queries for arbitrary ellipsoidal clusters.
problem Recovering clusters from same-cluster queries in arbitrary ellipsoidal clusters.
method Relaxing spherical k-means assumption to arbitrary ellipsoidal clusters, designing an algorithm with logarithmic query complexity. result Exact recovery of clusters using O(k3lnklnn) queries and ildeO(kn+k3) time. Paper proposes a new co-clustering method for overlapping clusters and outliers.
problem Real-world datasets often contain overlaps and outliers in co-clusters.
method Formulated Non-Exhaustive, Overlapping Co-Clustering problem and developed NEO-CC algorithm.
result NEO-CC algorithm effectively captures underlying co-clustering structure of real-world data.
Network Lasso clusters sparse graph clusters efficiently.
problem Local graph clustering of sparse and chain-like clusters.
method Network Lasso minimizes total variation of cluster indicator signals.
result Network Lasso handles sparse clusters difficult for spectral clustering.
DMClusts discovers multiple clusterings from multi-view data.
problem Finding multiple meaningful and diverse clusterings from multi-view data.
method Deep matrix factorization to gradually factorize multi-view data into representational subspaces and generate one clustering per layer, enforcing diversity through proximity minimization.
result DMClusts outperforms state-of-the-art multiple clustering solutions.
The paper connects two clustering methods by showing gradient ascent flow can move up the cluster tree.
problem Establishing a strong correspondence between clustering methods.
method Moving up the cluster tree by following the gradient ascent flow.
result Gradient ascent flow can be used to move up the cluster tree.
The paper introduces group-representative clustering to ensure fair representation of different groups in clusters.
problem Ensuring fair representation of different groups in clusters.
method Developed a new clustering approach called group-representative clustering, which parallels fairness notions in classification.
result Presented approximation algorithms for group representative k-median clustering and evaluated on real-world data. Paper proposes a new clustering model that preserves cluster recovery with fewer dimensions.
problem Clustering high-dimensional data with limited embedding dimensions.
method Randomly projected convex clustering model with improved embedding dimension.
result Cluster recovery can be preserved with fewer dimensions, independent of data points.
Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications. However, the existing deep clustering algorithms generally need the number of clusters in advance, which is usually unknown in…
Clustering is a widely used unsupervised learning method for finding structure in the data. However, the resulting clusters are typically presented without any guarantees on their robustness; slightly changing the used data sample or re-running a clustering algorithm involving some stochastic component may lead to comp…
FCA improves fair clustering by optimizing utility and fairness.
problem Balancing fairness and utility in clustering.
method FCA alternates between aligning data and optimizing cluster centers in an aligned space.
result FCA achieves a superior trade-off between fairness and utility.
New algorithm clusters hyperspectral images at multiple scales.
problem Clustering hyperspectral images at various scales.
method M-SRDL algorithm using spectral-spatial diffusion distances.
result More accurate clustering labels achieved with spatial regularization.
FBC clusters data fairly without needing cluster count.
problem Fairness in clustering groups of different sensitive groups.
method Developed a Bayesian model-based clustering method with a fair prior and efficient MCMC algorithm.
result Reasonably infers the number of clusters and achieves a fair utility trade-off.
Parameter-free clustering method using cluster catch digraphs (CCDs).
problem Finding the correct number of clusters in data without specifying a parameter.
method Hybrid of density-based and graph-based clustering methods using Ripley's K function.
result Minimum dominating sets of RK-CCDs estimate and distinguish clusters from noise.
New SDP algorithm recovers large clusters in SBM with small clusters of any size.
problem Graph clustering in SBM with large and small clusters.
method Semidefinite programming (SDP) with novel techniques to handle small clusters.
result Proves exact recovery of large clusters regardless of small cluster sizes.
A main task in data analysis is to organize data points into coherent groups or clusters. The stochastic block model is a probabilistic model for the cluster structure. This model prescribes different probabilities for the presence of edges within a cluster and between different clusters. We assume that the cluster ass…
With inspiration from Random Forests (RF) in the context of classification, a new clustering ensemble method---Cluster Forests (CF) is proposed. Geometrically, CF randomly probes a high-dimensional data cloud to obtain "good local clusterings" and then aggregates via spectral clustering to obtain cluster assignments fo…