MOSAIC decomposes user intent into three orthogonal components via a triple-encoder architecture with adversarial training and dynamic gating to outperform baselines in multi-domain session recommendations.
Graph neural networks in recommender systems: A survey,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
MOSAIC: Multi-Domain Orthogonal Session Adaptive Intent Capture for Prescient Recommendations
MOSAIC decomposes user intent into three orthogonal components via a triple-encoder architecture with adversarial training and dynamic gating to outperform baselines in multi-domain session recommendations.
-
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.