Papers
arxiv:2601.17787

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

Published on Jan 25
Authors:
,
,

Abstract

Generative recommender systems are enhanced through information-gain-based token weighting strategies that prioritize early tokens for semantic uncertainty reduction and rare tokens for popularity bias mitigation, combined with a multi-target learning framework using curriculum learning for stable optimization.

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2601.17787
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2601.17787 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2601.17787 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2601.17787 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.