What is the accuracy impact (Recall@k, NDCG@k) of replacing pretrained multimodal encoders (BERT/ViT) with lig

Abstract

Abstract: Streaming recommender systems (SRSs) are widely deployed in real-world applications, where user interests shift and new items arrive over time. As a result, effectively capturing users' latest preferences is challenging, as interactions reflecting recent interests are limited and new items often lack sufficient feedback. A common solution is to enrich item representations using multimodal encoders (e.g., BERT or ViT) to extract visual and textual features. However, these encoders are pretrained on general-purpose tasks: they are not tailored to user preference modeling, and they overlook the f

Research Question

What is the accuracy impact (Recall@k, NDCG@k) of replacing pretrained multimodal encoders (BERT/ViT) with lightweight, MoE-adapted encoders in streaming recommendation tasks when new item categories are introduced over time?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance