technique
Graph Attention Network
techniqueactiveprovisional
graph-attention-network-73e2ad41·1 events·first seen 18h agoAliases: Graph Attention Network
Co-occurring entities
More like this (12)
Graph Neural NetworksCross-Layer Sparse AttentionBlock Sparse AttentionProbSparse AttentionMiniMax Sparse AttentionLie-Algebra Attentionsparse attentionMulti-head Latent Attention (MLA)Graph Neural Network EncoderNeuronal Stochastic Attention Circuit (NSAC)Cross-Layer Sparse Attention with Shared RoutingGrouped-Query Attention
Recent events (1)
PromptGNN-sim: Bidirectional GNN-LLM fusion framework for text-attributed graph learning
Researchers introduce PromptGNN-sim, a bidirectional structure-semantic fusion framework that jointly trains a Graph Attention Network and an LLM for text-attributed graph learning. The system uses GAT-based neighborhood selection to generate structure-aware prompts for the LLM, with cross-modal contrastive learning and cross-attention aligning both components during training. Evaluated on six datasets including Cora, Pubmed, and WikiCS, it outperforms classical GNNs, standalone LLMs, and prior GNN-LLM fusion methods on cross-task transfer, cross-dataset generalization, and sparse perturbation settings.