Metraipolis › archive › dc_5baa8fbcaccc
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation — arXiv:2608.12845
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12845
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:18:11.571Z
- SHA-256 of the archived text
173f17f3502d4776f311e58003f7337a433eb02ce809f19c3ca7cf80e4dc7d30- Stable URL of this page
https://metraipolis.com/documento/dc_5baa8fbcaccc
How to cite
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation — arXiv:2608.12845 — arXiv (en), https://arxiv.org/abs/2608.12845 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5baa8fbcaccc (Metraipolis archive dc_5baa8fbcaccc, sha256 173f17f3502d4776f311e58003f7337a433eb02ce809f19c3ca7cf80e4dc7d30)
BibTeX
@misc{dc5baa8fbcaccc,
title = {FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation — arXiv:2608.12845},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12845},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5baa8fbcaccc; sha256 173f17f3502d4776f311e58003f7337a433eb02ce809f19c3ca7cf80e4dc7d30},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12845. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue, which we term \textbf{Token Frequency Bias}, where high-frequency SID tokens are systematically over-predicted while low-frequency SID tokens are under-predicted. This bias originates from the combined effects of imbalanced semantic codebooks during SID construction, and popularity bias together with the maximum likelihood estimation objective during recommendation training, resulting in unfair exposure across item categories. Existing SID methods mainly focus on improving codebook quality and overlook the impact of token frequency imbalance on downstream recommendation fairness, while LLM debiasing methods often yield suboptimal results when directly applied to SID-based recommendation, due to the hierarchical semantics of SID tokens. To address this issue, we propose \textbf{FSGR}, a fairness optimization framework for SID-based generative recommendation. During SID construction, FSGR employs OT-based Assignment Optimization and Dual-Criteria Re-anchor mechanism to form a more balanced SID representation space. During recommendation training, it adopts a two-stage training strategy and introduces Hierarchical Frequency Calibration for layer-specific fairness fine-tuning. Experiments on three public datasets with three backbone models demonstrate that FSGR mitigates token frequency bias and delivers an average Gini fairness improvement of over 20\% while maintaining competitive recommendation accuracy.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.12845 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:13:06.711Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).