#graph neural networks
82 papers · 1 filter
Scalable Rate-Splitting Precoding via Recurrent Structure-Preserving Graph Neural Networks
Wonseok Choi, Jeongjae Lee, Songnam Hong
The paper introduces a recurrent structure‑preserving graph neural network (RS‑GNN) that learns scalable precoders for rate‑splitting multiple access (RSMA) in multi‑user MISO syst…
A multi-scale feature enhanced graph neural network for fluid dynamics prediction in complex geometries
Li Xiao, Tianyu Li, Yiye Zou +2
The paper introduces ME-GNN, a multi‑scale feature enhanced graph neural network that combines two‑step message passing, an Attention U‑Net, and K‑hop sampling to predict fluid flo…
Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization
Chengcheng Yan, Qingsong Wang
The paper proposes a two‑view framework that aligns GNN embeddings with a structure‑free feature prior learned by an anchor network, and introduces a channel‑split adaptive gated G…
Comparative Analysis of GAT and BERT for Human-Like Playtesting
Kleio Fragkedaki, Theodoros Panagiotakopoulos, Matteo Biasielli +1
The paper compares transformer-based (BERT) and graph attention (GAT) models for predicting player behavior in Candy Crush Saga, showing they outperform CNN baselines on complex bo…
NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation
Guo Chen, Ziwen Li, Maolin Zheng +3
The paper proposes NGM-RAG, a framework that combines graph neural networks with text matching to improve retrieval-augmented generation for tasks requiring multi-hop reasoning and…
Learning Subgroup Relations Using Siamese Graph Neural Networks
Tal Weissblat
The paper introduces a Siamese graph neural network that encodes Cayley graph representations of finite groups to predict whether one group is a subgroup of another, achieving abou…