AlphaGalileo

Adapting to the Stream: An Instance-Attention GNN Method for Irregular Multivariate Time ...

DynIMTS replaces static graphs with instance-attention that updates edge weights on the fly, delivering SOTA imputation and P12 classification ...
IEEE

Communication-Aware Graph Neural Network for Multi-Agent Reinforcement Learning

Abstract: Multi-agent reinforcement learning (MARL) requires effective communication strategies to solve complex control tasks over uncertain communication channels. This paper explores a ...
IEEE

MCGC-Net: Multi-scale Controllable Graph Convolutional Network on Music Emotion Recognition

Abstract: This paper introduces a novel dynamic graph learning approach for frequency graphs, underpinned by a suite of baseline methodologies and the Multi-scale Controllable Graph Convolutional ...