Geometry-Aware Operator Families for Structured Representation Learning
cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Semi-Supervised Classification with Graph Convolutional Networks
- Graph Attention Networks
- Relational inductive biases, deep learning, and graph networks
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Sheaf Neural Networks
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Learning Not to Optimize: Physics-Informed Action-Space Reshaping for Intent-Based Network Control
- Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
- Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry
- Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes
- How Powerful are Graph Neural Networks?
- Metric-Gradient Projection for Stable Multi-Agent Policy Learning
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Operator-Guided Invariance Learning for Continuous Reinforcement Learning
- Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning
- Simplicial Neural Networks
- Geometry of Drifting MDPs with Path-Integral Stability Certificates
- Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks
- How Attentive are Graph Attention Networks?
- Predict then Propagate: Graph Neural Networks meet Personalized PageRank
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