DisCo improves cold-start cross-domain recommendation by disentangling user intents into K channels and aligning source-domain user similarities to target-domain similarities through contrastive learning.
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
-
DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation
DisCo improves cold-start cross-domain recommendation by disentangling user intents into K channels and aligning source-domain user similarities to target-domain similarities through contrastive learning.