REGER adds inter-item relations to generative recommendation with semantic IDs
The method pretrains by generating semantic neighbors' IDs and distills a teacher's full next-token distributions along the target path.
Stories per day · 30 days
1 RSS
Relatedrecommender-systems2semantic-ids2arxiv1jevrec1knowledge-distillation1preference-distillation1ranking1recommendation1semantic-identifiers1tiger1
3 stories, newest first · one card per story
Stories tagged #generative-recommendation
JevRec uses variable-length item codes for generative recommendation
On three public datasets it beat compared baselines and used less train and inference time than TIGER.
Distillation aligns item and code spaces for generative recommenders
Item Distribution Matching lifts average Recall@10 by 15.39%, and Code Marginal Matching lifts NDCG@10 by 8.28%.