<ul><li>Recommender systems often face the challenge of the user cold-start problem.</li><li>Cross-domain recommendation (CDR) is a solution to improve prediction performance in one domain using user interactions from another.</li><li>The DisCo framework proposes a graph-based disentangled contrastive learning approach to capture user intent and avoid negative transfer.</li><li>Experimental results demonstrate that DisCo outperforms existing baselines on benchmark CDR datasets.</li></ul>

DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation

Discover more