UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Zihan, Ma, Yufei, Qian, ZhiPeng, Dai, Huangyu, Wang, Zihan, Chen, Ben, Lei, Chenyi, Ding, Yuqing, Li, Han
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918127259877376
author Liang, Zihan
Ma, Yufei
Qian, ZhiPeng
Dai, Huangyu
Wang, Zihan
Chen, Ben
Lei, Chenyi
Ding, Yuqing
Li, Han
author_facet Liang, Zihan
Ma, Yufei
Qian, ZhiPeng
Dai, Huangyu
Wang, Zihan
Chen, Ben
Lei, Chenyi
Ding, Yuqing
Li, Han
contents Current e-commerce multimodal retrieval systems face two key limitations: they optimize for specific tasks with fixed modality pairings, and lack comprehensive benchmarks for evaluating unified retrieval approaches. To address these challenges, we introduce UniECS, a unified multimodal e-commerce search framework that handles all retrieval scenarios across image, text, and their combinations. Our work makes three key contributions. First, we propose a flexible architecture with a novel gated multimodal encoder that uses adaptive fusion mechanisms. This encoder integrates different modality representations while handling missing modalities. Second, we develop a comprehensive training strategy to optimize learning. It combines cross-modal alignment loss (CMAL), cohesive local alignment loss (CLAL), intra-modal contrastive loss (IMCL), and adaptive loss weighting. Third, we create M-BEER, a carefully curated multimodal benchmark containing 50K product pairs for e-commerce search evaluation. Extensive experiments demonstrate that UniECS consistently outperforms existing methods across four e-commerce benchmarks with fine-tuning or zero-shot evaluation. On our M-BEER bench, UniECS achieves substantial improvements in cross-modal tasks (up to 28\% gain in R@10 for text-to-image retrieval) while maintaining parameter efficiency (0.2B parameters) compared to larger models like GME-Qwen2VL (2B) and MM-Embed (8B). Furthermore, we deploy UniECS in the e-commerce search platform of Kuaishou Inc. across two search scenarios, achieving notable improvements in Click-Through Rate (+2.74\%) and Revenue (+8.33\%). The comprehensive evaluation demonstrates the effectiveness of our approach in both experimental and real-world settings. Corresponding codes, models and datasets will be made publicly available at https://github.com/qzp2018/UniECS.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13843
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion
Liang, Zihan
Ma, Yufei
Qian, ZhiPeng
Dai, Huangyu
Wang, Zihan
Chen, Ben
Lei, Chenyi
Ding, Yuqing
Li, Han
Information Retrieval
Artificial Intelligence
Current e-commerce multimodal retrieval systems face two key limitations: they optimize for specific tasks with fixed modality pairings, and lack comprehensive benchmarks for evaluating unified retrieval approaches. To address these challenges, we introduce UniECS, a unified multimodal e-commerce search framework that handles all retrieval scenarios across image, text, and their combinations. Our work makes three key contributions. First, we propose a flexible architecture with a novel gated multimodal encoder that uses adaptive fusion mechanisms. This encoder integrates different modality representations while handling missing modalities. Second, we develop a comprehensive training strategy to optimize learning. It combines cross-modal alignment loss (CMAL), cohesive local alignment loss (CLAL), intra-modal contrastive loss (IMCL), and adaptive loss weighting. Third, we create M-BEER, a carefully curated multimodal benchmark containing 50K product pairs for e-commerce search evaluation. Extensive experiments demonstrate that UniECS consistently outperforms existing methods across four e-commerce benchmarks with fine-tuning or zero-shot evaluation. On our M-BEER bench, UniECS achieves substantial improvements in cross-modal tasks (up to 28\% gain in R@10 for text-to-image retrieval) while maintaining parameter efficiency (0.2B parameters) compared to larger models like GME-Qwen2VL (2B) and MM-Embed (8B). Furthermore, we deploy UniECS in the e-commerce search platform of Kuaishou Inc. across two search scenarios, achieving notable improvements in Click-Through Rate (+2.74\%) and Revenue (+8.33\%). The comprehensive evaluation demonstrates the effectiveness of our approach in both experimental and real-world settings. Corresponding codes, models and datasets will be made publicly available at https://github.com/qzp2018/UniECS.
title UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2508.13843