GTFormer proposes replacing Transformer self-attention with a hierarchical graph neural network, achieving zero-shot length ...

A new simulation study presents a graph attention-based multi-agent reinforcement learning framework that jointly optimizes drone swarm trajectories, transmission power, and packet routing, reporting ...

A new graph neural network method called MADPGraph combines relation-aware multi-head attention with adaptive dynamic pruning ...

Document-level Event Factuality Identification (DEFI) has always been the focus of Information Extraction and Information Credibility. This paper studies a novel task named Evidential Document-level ...

Graph neural networks (GNNs) are a type of neural network architecture and deep learning method that can help users analyze graphs, enabling them to make predictions based on the data described by a ...

Financial fraud has evolved into increasingly sophisticated networks of deception, with criminals exploiting complex webs of transactions to launder money and coordinate elaborate schemes. Traditional ...