Saved in:
Bibliographic Details
Main Authors: Wang, Jinzhi, Li, Bin, Peng, Qingke, Li, Haozhou, Zeng, Zeyuan, Li, Ruimeng, Yang, Kaixuan, Zhang, Jiangbo, Zhou, Biyi, Wang, Yaoying
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04722
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915400194719744
author Wang, Jinzhi
Li, Bin
Peng, Qingke
Li, Haozhou
Zeng, Zeyuan
Li, Ruimeng
Yang, Kaixuan
Zhang, Jiangbo
Zhou, Biyi
Wang, Yaoying
author_facet Wang, Jinzhi
Li, Bin
Peng, Qingke
Li, Haozhou
Zeng, Zeyuan
Li, Ruimeng
Yang, Kaixuan
Zhang, Jiangbo
Zhou, Biyi
Wang, Yaoying
contents Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrifices diversity and exacerbates the cold-start problem. An empirical analysis of DCRS and statistics on the REDIAL corpus show that only 10% of head movies account for nearly half of all mentions, whereas about 70% of tail movies receive merely 26% of the attention. This imbalance gives rise to three critical challenges: head over-fitting, body representation drift, and tail sparsity. To address these issues, we propose LumiCRS, an end-to-end framework that mitigates long-tail imbalance through three mutually reinforcing layers: (i) an Adaptive Comprehensive Focal Loss (ACFL) that dynamically adjusts class weights and focusing factors to curb head over-fitting and reduce popularity bias; (ii) Prototype Learning for Long-Tail Recommendation, which selects semantic, affective, and contextual prototypes to guide clustering and stabilize body and tail representations; and (iii) a GPT-4o-driven prototype-guided dialogue augmentation module that automatically generates diverse long-tail conversational snippets to alleviate tail sparsity and distribution shift. Together, these strategies enable LumiCRS to markedly improve recommendation accuracy, diversity, and fairness: on the REDIAL and INSPIRED benchmarks, LumiCRS boosts Recall@10 and Tail-Recall@10 by 7-15% over fifteen strong baselines, while human evaluations confirm superior fluency, informativeness, and long-tail relevance. These results demonstrate the effectiveness of multi-layer collaboration in building an efficient and fair long-tail conversational recommender.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04722
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Recommender Systems
Wang, Jinzhi
Li, Bin
Peng, Qingke
Li, Haozhou
Zeng, Zeyuan
Li, Ruimeng
Yang, Kaixuan
Zhang, Jiangbo
Zhou, Biyi
Wang, Yaoying
Artificial Intelligence
Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrifices diversity and exacerbates the cold-start problem. An empirical analysis of DCRS and statistics on the REDIAL corpus show that only 10% of head movies account for nearly half of all mentions, whereas about 70% of tail movies receive merely 26% of the attention. This imbalance gives rise to three critical challenges: head over-fitting, body representation drift, and tail sparsity. To address these issues, we propose LumiCRS, an end-to-end framework that mitigates long-tail imbalance through three mutually reinforcing layers: (i) an Adaptive Comprehensive Focal Loss (ACFL) that dynamically adjusts class weights and focusing factors to curb head over-fitting and reduce popularity bias; (ii) Prototype Learning for Long-Tail Recommendation, which selects semantic, affective, and contextual prototypes to guide clustering and stabilize body and tail representations; and (iii) a GPT-4o-driven prototype-guided dialogue augmentation module that automatically generates diverse long-tail conversational snippets to alleviate tail sparsity and distribution shift. Together, these strategies enable LumiCRS to markedly improve recommendation accuracy, diversity, and fairness: on the REDIAL and INSPIRED benchmarks, LumiCRS boosts Recall@10 and Tail-Recall@10 by 7-15% over fifteen strong baselines, while human evaluations confirm superior fluency, informativeness, and long-tail relevance. These results demonstrate the effectiveness of multi-layer collaboration in building an efficient and fair long-tail conversational recommender.
title LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Recommender Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2507.04722