Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities.

@inproceedings{ye-2026-multimodal, author = {Yu Ye and Junchen Fu and Yu Song and Kaiwen Zheng and Joemon M. Jose}, editor = {Ricardo Campos and Adam Jatowt and Yanyan Lan and Mohammad Aliannejadi and Christine Bauer and Sean MacAvaney and Avishek Anand and Zhaochun Ren and Suzan Verberne and Nan Bai and Masoud Mansoury}, title = {{Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities}}, booktitle = {{Advances in Information Retrieval - 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 - April 2, 2026, Proceedings, Part III}}, series = {Lecture Notes in Computer Science}, volume = {16485}, pages = {66--81}, publisher = {Springer}, year = {2026}, url = {https://doi.org/10.1007/978-3-032-21324-2_5}, doi = {https://doi.org/10.1007/978-3-032-21324-2_5} }