ContextGNN fuses local pair-wise graph scores with a shallow-item two-tower fallback and a learned per-user offset, improving average MAP by about 20% over NBFNet on RelBench.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ContextGNN: Beyond Two-Tower Recommendation Systems
ContextGNN fuses local pair-wise graph scores with a shallow-item two-tower fallback and a learned per-user offset, improving average MAP by about 20% over NBFNet on RelBench.