Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Token-Weighted Multi-Target Learning for Generative Recommenders with Curriculum Learning

About

Generative recommender systems have recently attracted attention by formulating next-item prediction as an autoregressive sequence generation task. However, most existing methods optimize standard next-token likelihood and implicitly treat all tokens as equally informative, which is misaligned with semantic-ID-based generation. Accordingly, we propose two complementary information-gain-based token-weighting strategies tailored to generative recommendation with semantic IDs. Front-Greater Weighting captures conditional semantic information gain by prioritizing early tokens that most effectively reduce candidate-item uncertainty given their prefixes and encode coarse semantics. Frequency Weighting models marginal information gain under long-tailed item and token distributions, upweighting rare tokens to counteract popularity bias. Beyond individual strategies, we introduce a multi-target learning framework with curriculum learning that jointly optimizes the two token-weighted objectives alongside standard likelihood, enabling stable optimization and adaptive emphasis across training stages. Extensive experiments on benchmark datasets show that our method consistently outperforms strong baselines and existing token-weighting approaches, with improved robustness, strong generalization across different semantic-ID constructions, and substantial gains on both head and tail items. Code is available at https://github.com/CHIUWEINING/Token-Weighted-Multi-Target-Learning-for-Generative-Recommenders-with-Curriculum-Learning.

Wei-Ning Chiu, Chuan-Ju Wang, Pu-Jen Cheng• 2026

Related benchmarks

TaskDatasetResultRank
Sequential RecommendationMovieLens 1M (test)
Hit@1027.27
22
Sequential RecommendationYelp (test)
H@104.19
19
Sequential RecommendationMusical Instruments Amazon (test)
Hit Rate @ 50.033
8
Sequential RecommendationAmazon Industrial and Scientific (test)
H@50.0255
8
Showing 4 of 4 rows

Other info

Follow for update