Improved (O(pw), Δ)-LDD for pathwidth-pw digraphs and O(tw log n) integrality gap for directed sparsest-cut LP on treewidth-tw graphs via refined quasipartition analysis.
Neural Comput
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 11roles
background 3polarities
background 3representative citing papers
ScaleMAP is a dimensionality-reduction method that preserves both neighborhood structure and local density by scaling embedding displacements with original local radii, matching DensMAP on density while retaining UMAP-level neighborhood fidelity.
AMLE graph value extensions meet a local action-gap certificate guaranteeing goal-reaching greedy rollouts under argmin-Q planning and achieve 0.97 success on AntMaze-derived graphs versus 0.58 for harmonic extension.
GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
Empirical integral operators with discontinuous non-negative symmetric kernels converge spectrally to their population versions with explicit rates as sample size grows to infinity.
UHD-GCN-BIQA models structural dependencies among sampled patches via a hybrid kNN graph and residual graph convolutions to achieve competitive PLCC and SRCC with the lowest RMSE on the UHD-IQA benchmark for blind ultra-high-definition image quality assessment.
CADI quantifies the preservation of relative cluster angles in low-dimensional projections using internal angles from point triples.
LoGraB creates fragmented graph benchmarks with controls for radius, spectral quality, noise, and coverage, while AFR reconstructs faithful graph islands from spectral patches using fidelity scoring, RANSAC-Procrustes alignment, and adaptive stitching, supported by recovery proofs and strong results
A spectral framework for nonlinear DR uses spectral bases plus cross-entropy optimization to create multi-scale embeddings that preserve both global manifold geometry and local neighborhoods while supporting graph-frequency analysis.
MAPLE enhances UMAP via self-supervised MMCRs to untangle complex manifolds, yielding clearer clusters and finer subclusters than standard UMAP at similar cost.
Short histories of observations can recover the underlying manifold for transporting discontinuous densities when direct source-target pairs are insufficient due to folds or marginalization.
citing papers explorer
-
Directed Low Diameter Decomposition for Structured Digraphs
Improved (O(pw), Δ)-LDD for pathwidth-pw digraphs and O(tw log n) integrality gap for directed sparsest-cut LP on treewidth-tw graphs via refined quasipartition analysis.
-
ScaleMAP: Preserving Local Density and Neighborhood Structure in Low-Dimensional Embeddings
ScaleMAP is a dimensionality-reduction method that preserves both neighborhood structure and local density by scaling embedding displacements with original local radii, matching DensMAP on density while retaining UMAP-level neighborhood fidelity.
-
Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning
AMLE graph value extensions meet a local action-gap certificate guaranteeing goal-reaching greedy rollouts under argmin-Q planning and achieve 0.97 success on AntMaze-derived graphs versus 0.58 for harmonic extension.
-
GravityGraphSAGE: Link Prediction in Directed Attributed Graphs
GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
-
Spectral convergence of empirical integral operators with discontinuous kernels
Empirical integral operators with discontinuous non-negative symmetric kernels converge spectrally to their population versions with explicit rates as sample size grows to infinity.
-
Ultra-High-Definition Image Quality Assessment via Graph Representation Learning
UHD-GCN-BIQA models structural dependencies among sampled patches via a hybrid kNN graph and residual graph convolutions to achieve competitive PLCC and SRCC with the lowest RMSE on the UHD-IQA benchmark for blind ultra-high-definition image quality assessment.
-
Class Angular Distortion Index for Dimensionality Reduction
CADI quantifies the preservation of relative cluster angles in low-dimensional projections using internal angles from point triples.
-
Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction
LoGraB creates fragmented graph benchmarks with controls for radius, spectral quality, noise, and coverage, while AFR reconstructs faithful graph islands from spectral patches using fidelity scoring, RANSAC-Procrustes alignment, and adaptive stitching, supported by recovery proofs and strong results
-
A Spectral Framework for Multi-Scale Nonlinear Dimensionality Reduction
A spectral framework for nonlinear DR uses spectral bases plus cross-entropy optimization to create multi-scale embeddings that preserve both global manifold geometry and local neighborhoods while supporting graph-frequency analysis.
-
MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis
MAPLE enhances UMAP via self-supervised MMCRs to untangle complex manifolds, yielding clearer clusters and finer subclusters than standard UMAP at similar cost.
-
A geometric approach to the transport of discontinuous densities
Short histories of observations can recover the underlying manifold for transporting discontinuous densities when direct source-target pairs are insufficient due to folds or marginalization.