DG-SA-GNN dynamically constructs four user similarity graphs from different measures, fuses them with a Graph Transformer and CrossAttention, and reports Recall@20 of 0.162 on MovieLens100K, outperforming LightGCN in recall.
Recommender systems survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamic Graph with Similarity-Aware Attention Graph Neural Network for Recommender Systems
DG-SA-GNN dynamically constructs four user similarity graphs from different measures, fuses them with a Graph Transformer and CrossAttention, and reports Recall@20 of 0.162 on MovieLens100K, outperforming LightGCN in recall.