Rooted motif signatures determine latent position connectivity profiles for generic finite-rank graphons and yield empirical estimators with concentration bounds from a single observed graph.
International Conference on Learning Representations , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
Cardiac Mesh Flow generates 3D+t four-chamber cardiac meshes with anatomical correspondence and volume conditioning via one-step flow matching on multi-scale deformation fields.
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
LHSD estimates local intrinsic dimension in high-D spaces by spectral filtering of the log-density Hessian via SLQ to isolate zero-curvature tangent directions.
citing papers explorer
-
Beyond Degree: Rooted Motif Signatures for Latent Position Identifiability in Graphon Models
Rooted motif signatures determine latent position connectivity profiles for generic finite-rank graphons and yield empirical estimators with concentration bounds from a single observed graph.
-
Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
-
Cardiac Mesh Flow: One-Step Generation of 3D+t Cardiac Four-Chamber Meshes via Flow Matching
Cardiac Mesh Flow generates 3D+t four-chamber cardiac meshes with anatomical correspondence and volume conditioning via one-step flow matching on multi-scale deformation fields.
-
Are Candidate Models Really Needed for Active Learning?
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD estimates local intrinsic dimension in high-D spaces by spectral filtering of the log-density Hessian via SLQ to isolate zero-curvature tangent directions.