FROG makes full-resolution graph structure learnable in relational deep learning by modeling table roles as optimizable components in message passing, regularized by functional dependency constraints.
A survey on graph structure learning: Progress and opportunities
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
LAGA is a unified multi-agent LLM framework that automates comprehensive quality optimization for text-attributed graphs by running detection, planning, action, and evaluation agents in a closed loop.
Unsupervised symmetry discovery via shallow group-convolutional networks recovers latent domains from linear measurements of random fields by learning symmetry actions under stationarity and locality constraints.
CRiTIC improves robustness of trajectory predictions against non-causal agents by up to 54% and cross-domain performance by up to 29% via a Causal Discovery Network and Causal Attention Gating in a Transformer.
DEGfM is a dynamic elliptical graph factor model that performs Riemannian optimization on the Grassmann manifold with geodesic temporal regularization to infer time-varying precision matrices.
citing papers explorer
-
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
FROG makes full-resolution graph structure learnable in relational deep learning by modeling table roles as optimizable components in message passing, regularized by functional dependency constraints.
-
When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
LAGA is a unified multi-agent LLM framework that automates comprehensive quality optimization for text-attributed graphs by running detection, planning, action, and evaluation agents in a closed loop.
-
Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery
Unsupervised symmetry discovery via shallow group-convolutional networks recovers latent domains from linear measurements of random fields by learning symmetry actions under stationarity and locality constraints.
-
Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving
CRiTIC improves robustness of trajectory predictions against non-causal agents by up to 54% and cross-domain performance by up to 29% via a Causal Discovery Network and Causal Attention Gating in a Transformer.
-
Dynamic Elliptical Graph Factor Models via Riemannian Optimization with Geodesic Temporal Regularization
DEGfM is a dynamic elliptical graph factor model that performs Riemannian optimization on the Grassmann manifold with geodesic temporal regularization to infer time-varying precision matrices.