A multimodal recommender that trains without graph convolution and applies it only at test time outperforms graph-trained baselines while training much faster.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Best is Yet to Come: Graph Convolution in the Testing Phase for Multimodal Recommendation
A multimodal recommender that trains without graph convolution and applies it only at test time outperforms graph-trained baselines while training much faster.