PANDA: Prior-guided Attentional Dual-path Architecture
cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/jainris/panda
Sources
- Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
- Preventing Over-Smoothing for Hypergraph Neural Networks
- HNHN: Hypergraph Networks with Hyperedge Neurons
- Adam: A Method for Stochastic Optimization
- Normalized Attention Without Probability Cage
- Directed hypergraph neural network
- Graph Attention Networks
- Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective
- Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks