Long-Tail Recommendation

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation
Oct 12, 2026Tripti Shukla, Shwetha Somasundaram, Akshat Gupta +3Long-Tail Recommendation Recommender Systems
Glance Bengaluru, India · Glance Vilnius, Lithuania · Glance London, United Kingdom
Soft Curriculum Learning for Optimizing Fresh and Generalized Recommendations
Aug 11, 2026Arnab Bhadury, Siyan Zheng, Anlan Yu +6Popularity Bias Long-Tail Recommendation
Google Vancouver, BC, Canada · Google Mountain View, CA, USA
MESH: Scaling Up Retrieval with Heterogeneous Content Unification
Jul 14, 2026Jiaxing Qu, Yilin Chen, Junpeng Hou +4Long-Tail Recommendation Recommender Systems
Pinterest Inc. San Francisco, CA, USA
Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces
Jul 10, 2026Syed Mohammed Arshad Zaidi, Eric Rincon, Shayan HassantabarSemantic Search Long-Tail Recommendation
Expedia Group Austin, Texas, USA
Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval
Jun 3, 2026Olivier JeunenLong-Tail Recommendation Recommender Systems
aampe · Antwerp, Belgium
Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems
Mar 13, 2026Jiaming Zhang, Yuyuan Li, Xiaohua Feng +4Long-Tail Recommendation Recommender Systems
Zhejiang University Hangzhou, Zhejiang, China · Hangzhou Dianzi University Hangzhou, Zhejiang, China · Ant Group Hangzhou, Zhejiang, China
Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation
Mar 3, 2026Chongjun Xia, Xiaoyu Shi, Hong Xie +3Long-Tail Recommendation Fairness in Recommender Systems
Chinese Academy of Sciences · University of Technology Sydney · University of Science and Technology of China
The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation
Dec 11, 2025Ziwei Liu, Yejing Wang, Wanyu Wang +6Semantic ID Recommendation Sequential Recommendation
City University of Hong Kong Hong Kong, China · Tongji University Shanghai, China · Xi’an Jiaotong University Xi’an, China +3

Oct 12, 2026J/K move · Enter open · S save

HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation

Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg+2

Glance Bengaluru, India · Glance Vilnius, Lithuania · Glance London, United Kingdom

Long-Tail Recommendation Recommender Systems Generative Recommendation Hierarchical Representation Learning

Open paper AskPDF arXiv

Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively. We introduce an approach showing that explicitly incorporating hierarchical and attribute-level supervision into generative recommendation can simultaneously improve training efficiency and long-tail recommendation performance. Existing approaches typically optimize semantic ID prediction with a standard causal cross-entropy objective, which does not explicitly exploit the hierarchical structure of semantic IDs and can require substantial training to learn effective item representations. Moreover, data-sparse tail items often suffer from poor representations due to limited supervision, resulting in weaker long-tail recommendation performance. We address these challenges with HASTE (Hierarchical and Attribute-aware Supervision for generaTive rEcommendation), a unified training framework that introduces hierarchical and attribute-specific supervision. HASTE's Hierarchical Loss explicitly exploits the multi-level structure of semantic IDs, providing supervision at each level of the item hierarchy and substantially accelerating training convergence. Its Attribute-Specific Losses encourage the model to preserve fine-grained item attributes, leveraging the language model's inherent semantic knowledge to improve representations and recommendations for tail items. We extensively evaluate HASTE on a fashion recommendation benchmark and across multiple domains of the Amazon dataset. HASTE improves recommendation performance across datasets and item-frequency regimes. Notably, the Hierarchical Loss achieves approximately 2x faster convergence than the standard causal cross-entropy objective, substantially improving training efficiency while maintaining strong recommendation quality.