Adversarial approach improves extreme multi-label classification performance.
problem Learning relevant labels from datasets with many rare labels.
method Robust optimization framework with Hamming loss for tail-label detection.
result Proved efficacy of Hamming loss and improved performance over state-of-the-art methods.
HAXMLNet tackles extreme multi-label text classification with hierarchical attention.
problem Tagging each text with relevant labels from an extreme-scale label set.
method Proposes a hierarchical structure with multi-label attention for efficient and effective XMTC.
result HAXMLNet achieves competitive performance compared to state-of-the-art methods.
Efficient graph-based decoding improves extreme classification accuracy.
problem Learning algorithms for extreme classification with large label sets.
method ECOC with loss-based decoding on graph-induced output codes.
result Efficient loss-based decoding on graph output codes improves classification accuracy.
DEFRAG accelerates extreme classification by reducing feature dimensions.
problem High precision and scalability in assigning labels from a vast label space.
method Adaptive feature agglomeration to reduce feature dimensions.
result Significant reduction in training and prediction times (up to 40%) for extreme classification algorithms.
New classifiers tackle unknown classes with extreme value theory.
problem Classifiers struggle with unknown classes having different geometries.
method Proposes two new classifiers based on extreme value theory approximations.
result New classifiers outperform existing methods in simulations and real datasets.
BP pretreatment reduces multi-label classification time.
problem Efficiently annotate large label sets for extreme multi-label classification.
method Divide instances into clusters, attach most relevant labels, train on pairs of clusters.
result BP reduces prediction time significantly without sacrificing accuracy.
The paper classifies rotationally symmetric extremal Kähler metrics on complex manifolds.
problem Classifying extremal Kähler metrics on complex manifolds.
method Analyzing polynomial zeros in Calabi's extremal equation.
result No U ( n ) U(n) U ( n ) invariant complete extremal Kähler metrics on C n \mathbb C^n C n with positive bisectional curvature. New loss functions improve extreme classification with missing labels.
problem Large number of infrequent labels and missing labels in XMC.
method Derive unbiased loss functions for XMC, incorporating them into existing algorithms.
result Significant improvement in extreme classification performance (up to 20%) over existing methods.
RELM uses rough set theory to improve ELM's classification accuracy for high-dimensional data.
problem Improving classification accuracy for high-dimensional data.
method RELM uses rough set theory to divide data into upper and lower approximation sets, and applies attribute reduction to enhance performance.
result RELM achieves better accuracy and repeatability compared to comparison algorithms.
Extreme classification problems are multiclass and multilabel classification problems where the number of outputs is so large that straightforward strategies are neither statistically nor computationally viable. One strategy for dealing with the computational burden is via a tree decomposition of the output space. Whil…
APLC-XLNet improves XMTC by clustering labels and reducing computational time.
problem Efficiently tagging texts with many labels from a large set.
method Fine-tunes XLNet with APLC to approximate cross entropy loss.
result Achieved state-of-the-art results on XMTC benchmarks.
We classify extremal curves in free nilpotent Lie groups. The classification is obtained via an explicit integration of the adjoint equation in Pontryagin Maximum Principle. It turns out that abnormal extremals are precisely the horizontal curves contained in algebraic varieties of a specific type. We also extend the r…
Paper proposes an approximate margin method for fast multi-class classification.
problem Challenges in multi-class classification with many classes.
method Uses ANN search structures and LSH for approximate margin estimation.
result Approximate margin method is highly competitive in time, memory, and performance.
Paper proposes AdaBoost-assisted ELM for efficient online sequential classification.
problem Efficient online sequential classification with improved accuracy and stability.
method Utilizes AdaBoost for cost-sensitive learning and forgetting mechanism for stability.
result Achieves 94.41% accuracy on MNIST dataset with reduced standard deviation.
Classification of G2-structures on Lie groups with Ricci pinched conditions.
problem Classifying G2-structures on Lie groups under specific geometric conditions.
method Complete classification of left-invariant closed G2-structures on Lie groups, extremally Ricci pinched, up to equivalence and scaling.
result Five distinct G2-structures on five different completely solvable Lie groups, with one unimodular case being exact.
Paper proposes an adversarial sampling method for efficient extreme classification.
problem Training classifiers over many classes is computationally expensive.
method Adversarial sampling to draw negative samples from an adversarial model.
result Significantly reduces training time by an order of magnitude.
Proves rigidity of extremal Kerr-Newman horizons.
problem Classifying near-horizon geometries of extremal Kerr-Newman horizons.
method Proves intrinsic geometry constraints leading to rigidity.
result Proves extremal Kerr-Newman horizons are unique.
MACH reduces memory usage for extreme classification by hashing.
problem Expensive training of deep models with large softmax layers.
method Merged-Average Classifiers via Hashing (MACH) using count-min sketch.
result Significant memory reduction and training speedup.
Forest tree species mapped with high accuracy using satellite data.
problem Classifying dominant tree species in Swedish forests.
method Extreme gradient boosting model with Bayesian optimization, combining Sentinel-1/2 satellite data and field observations.
result Overall accuracy of 85%, F1 score of 0.82, Matthews correlation coefficient of 0.81.
A simple baseline for extreme multi-label classification using random projections.
problem Automatically annotating data points with relevant labels from a large label vocabulary.
method On-the-fly global embedding using random projections, with an ensemble of learners.
result Competitive accuracy compared to existing methods, with significant speed-up and model-size reduction.
Classifies automorphisms of conformally Kähler, Einstein-Maxwell metrics.
problem Classifying holomorphic automorphisms of conformally Kähler, Einstein-Maxwell metrics.
method Structure theorem for holomorphic automorphisms, extending classical results.
result Completes classification of conformally Kähler, Einstein--Maxwell metrics on C P 1 i m e s C P 1 \mathbb{CP}^1 imes \mathbb{CP}^1 CP 1 im es CP 1 . Extremely Fast Decision Tree improves accuracy on large datasets.
problem Improving accuracy on large classification datasets.
method Hoeffding Anytime Tree, a modified version of Hoeffding Tree.
result Extremely Fast Decision Tree achieves superior prequential accuracy on most UCI datasets.
Extreme multi-label classification refers to supervised multi-label learning involving hundreds of thousands or even millions of labels. Datasets in extreme classification exhibit fit to power-law distribution, i.e. a large fraction of labels have very few positive instances in the data distribution. Most state-of-the-…
AF improves classification models by adaptively weighting trees.
problem Improving classification model performance.
method AF combines OP2T for input-dependent weights and MIO for dynamic refinement.
result AF consistently outperforms RF, XGBoost, and other weighted RF.
We present a local classification of conformally equivalent but oppositely oriented 4-dimensional Kaehler metrics which are toric with respect to a common 2-torus action. In the generic case, these "ambitoric" structures have an intriguing local geometry depending on a quadratic polynomial q and arbitrary functions A a…
Study classifies special metrics on specific surfaces.
problem Classifying extremal Kähler metrics with singularities.
method Analyzes Hessian of the Curvature of the Metric on K-surfaces.
result Identifies non-CSC HCMU metrics on S { α } 2 S^2_{\{α\}} S { α } 2 and S { α , β } 2 S^2_{\{α,β\}} S { α , β } 2 . XR-Transformer accelerates XMC by recursively fine-tuning on multi-resolution objectives.
problem Efficiently classifying texts with large label sets.
method Recursive multi-resolution fine-tuning of transformers.
result XR-Transformer achieves 20x faster training time and 54% Precision@1 on Amazon-3M.
New maximal surfaces solve Bernstein problems.
problem Bernstein problems in centroaffine geometry.
method Calabi affine maximal surfaces and orthonormal frame fields.
result Complete centroaffine extremal hypersurfaces solve all Bernstein problems.
Study finds conditions for Kähler-Einstein metrics on flag manifolds.
problem Characterizing Kähler-Einstein metrics on flag manifolds.
method Using Lie theoretic data, establish a sufficient and necessary condition for λ 1 λ_1 λ 1 -extremality. result Identifies criteria for a metric to be a critical point of the first eigenvalue functional.
A scalable Gaussian process method for large datasets.
problem Handling high number of training instances and high dimensional input data.
method Subspace inducing inputs combined with matrix-preconditioning.
result Improved predictive performances and reduced computational times.
The study identifies extremal dependence in financial markets using a bootstrap-based testing procedure.
problem Accurately identifying extremal dependence in multivariate heavy-tailed financial data.
method Bootstrap-based testing procedure applied to U.S. and Chinese stock returns.
result The U.S. exhibits more isolated clustering of dependent assets compared to China.
Probabilistic label trees improve XMLC by organizing labels hierarchically.
problem Efficiently tagging instances with a small subset of relevant labels from a large pool.
method Introduce and analyze probabilistic label trees (PLTs) as a generalization of hierarchical softmax for multi-label problems.
result PLTs are consistent for various performance metrics and can be trained online without prior knowledge.
We give a systematic method to calculate some homological data from the global monodromy of a topological elliptic surface. We apply this method to the cases 1) the transcendental lattice of an extremal elliptic K3 surface, 2) the torsion part of Mordell-Weil group of a general elliptic surface, and 3) the Mordell-Weil…
Extreme value theory enhances statistical learning extrapolation for rare events.
problem Challenges in traditional machine learning methods for extreme data.
method Asymptotic theory and statistical tools for tail behavior.
result Effective extrapolation methods for extreme quantiles and anomalies.
X-Transformer improves deep transformer performance on extreme multi-label text classification.
problem Classifying text with a large number of labels from a sparse label space.
method Fine-tuning deep transformer models for extreme multi-label text classification.
result X-Transformer achieves new state-of-the-art results on XMC benchmark datasets.
Classifies Fano varieties with large pseudoindex and non-free rational curves.
problem Classifying Fano varieties with specific properties.
method Extremal contractions and classification of varieties.
result Complete classification of Fano n n n -folds with pseudoindex at least n − 2 n-2 n − 2 and Picard number greater than one. Introduces RMEE for robust classification, improving MEE's performance in noisy conditions.
problem Improving robustness of MEE criterion for noisy classification.
method Analyzed optimal error distribution, introduced RMEE with half-quadratic optimization.
result RMEE achieves better robustness in noisy conditions compared to original MEE.
Classifies states of four rebits using group theory.
problem Classifying states of four rebits in quantum information theory.
method Group theory, specifically G ^ ( R ) \widehat{G}(\mathbb R) G ( R ) -module construction and Galois cohomology. result Semisimple and mixed orbits of four rebits are classified.
CascadeXML improves multi-resolution learning for XMC with transformer features.
problem Learning subset labels from millions of choices with trade-offs between performance and computation.
method End-to-end multi-resolution learning pipeline using transformer multi-layer architecture.
result Significantly outperforms existing approaches on benchmark datasets.
A new method for fast XMLC using IR vector space model.
problem Handling many labels in extreme multi-label classification.
method Sparse Weighted Nearest-Neighbor Method derived from SOTA linear classifiers.
result Equivalent performance to SOTA models on large datasets.
A classification of 2-dimensional surfaces imbedded in spacetime is presented, according to the algebraic properties of their shape tensor. The classification has five levels, and provides among other things a refinement of the concepts of trapped, umbilical and extremal surfaces, which split into several different cla…
Novel semi-supervised method for X-ray classification with minimal labels.
problem Classifying X-ray data with limited labeled data.
method Graph-based semi-supervised learning with carefully selected class priors.
result Competitive results on ChestX-ray14 data set with reduced need for annotated data.
This work analyzes label embedding for large multiclass classification problems.
problem Label embedding for large multiclass classification problems.
method Analysis of label embedding in extreme multiclass classification, presenting an excess risk bound and showing a trade-off between computational and statistical efficiency.
result The statistical penalty for label embedding vanishes with sufficiently low coherence under the Massart noise condition.
The paper studies extremal hypersurfaces in ellipsoids using centro-affine geometry.
problem Characterizing extremal hypersurfaces in centro-affine geometry.
method Analyzing invariant submanifold flows and deriving variational formulas.
result Circles on S 2 ( 1 ) \mathbb{S}^2(1) S 2 ( 1 ) with radius 6 / 3 \sqrt{6}/3 6 /3 are equi-centro-affine maximal. Paper proposes a method to identify wind hazard types and predict extreme wind speeds.
problem Difficulty in identifying wind hazard types from meteorological data records.
method Numerical pattern recognition method with feature extraction and generalization.
result Algorithm performance validated using K-fold cross-validation and real-world data.
Proves intrinsic rigidity of extremal horizons, classifying their geometry.
problem Classifying the intrinsic geometry of extremal horizons.
method Proves existence of Killing vector fields and solves PDEs.
result Proves most general solution for extremal Kerr horizon and classifies near-horizon geometries.
The paper provides bounds for the empirical angular measure and applies them to improve statistical learning in extreme regions.
problem Estimating the angular measure in high-dimensional data with different distributions.
method Established bounds for the maximal deviations of the empirical angular measure from the true measure, using rank transformation and analyzing the most extreme observations.
result The bounds provide performance guarantees for statistical learning procedures in extreme regions, such as binary classification and anomaly detection.
The paper classifies electrovacuum spaces in higher dimensions, proving several key results.
problem Classifying regular static black hole solutions of the static Einstein-Maxwell equations.
method Analytical proofs and geometric analysis of electrovacuum spaces.
result An n-dimensional locally conformally flat extremal electrovacuum space must be in the Majumdar-Papapetrou class.