Search Results for author:
Found 4 papers, 1 papers with code
Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning
HNSD operates via normalized degree zero sheaf Laplacians over symmetric simplicial sets, resolving orientation ambiguity and adjacency sparsity inherent to hypergraph learning.
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning
Offline multi-agent reinforcement learning (MARL) is increasingly recognized as crucial for effectively deploying RL algorithms in environments where real-time interaction is impractical, risky, or costly.
Non-backtracking Graph Neural Networks
In this work, we propose to resolve such a redundancy issue via the non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node.
Automated Solubility Analysis System and Method Using Computer Vision and Machine Learning
The proposed system is a combination of a device that uses a background image and a method for estimating the dissolution and particle presence by changing the background image.
