Learning to Approximate Uniform Facility Location via Graph Neural Networks
cs.LG, cs.DS, cs.NE, stat.ML
Submitted: 2026-02-13
Updated: 2026-09-23
Terminology
Sources
- Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
- Neural Combinatorial Optimization with Reinforcement Learning
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Simpler Analyses of Local Search Algorithms for Facility Location
- Primal-Dual Neural Algorithmic Reasoning
- On Transferring Transferability: Towards a Theory for Size Generalization
- Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement
- Geometric Algorithms for Neural Combinatorial Optimization with Constraints
- A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks
- Guiding High-Performance SAT Solvers with Unsat-Core Predictions
- Graph neural networks extrapolate out-of-distribution for shortest paths
- Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation
- Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs
- Survey on Generalization Theory for Graph Neural Networks
- Understanding Generalization in Node and Link Prediction
- Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers
- Fully-inductive Node Classification on Arbitrary Graphs
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks