Multimodal recommender systems: A survey
The recommender system (RS) has been an integral toolkit of online services. They are
equipped with various deep learning techniques to model user preference based on …
equipped with various deep learning techniques to model user preference based on …
A comprehensive survey on multimodal recommender systems: Taxonomy, evaluation, and future directions
Recommendation systems have become popular and effective tools to help users discover
their interesting items by modeling the user preference and item property based on implicit …
their interesting items by modeling the user preference and item property based on implicit …
Large language models meet collaborative filtering: An efficient all-round llm-based recommender system
Collaborative filtering recommender systems (CF-RecSys) have shown successive results in
enhancing the user experience on social media and e-commerce platforms. However, as CF …
enhancing the user experience on social media and e-commerce platforms. However, as CF …
Multimodal pretraining, adaptation, and generation for recommendation: A survey
Personalized recommendation serves as a ubiquitous channel for users to discover
information tailored to their interests. However, traditional recommendation models primarily …
information tailored to their interests. However, traditional recommendation models primarily …
Map: A model-agnostic pretraining framework for click-through rate prediction
With the widespread application of online advertising systems, click-through rate (CTR)
prediction has received more and more attention and research. The most prominent features …
prediction has received more and more attention and research. The most prominent features …
MISSRec: Pre-training and transferring multi-modal interest-aware sequence representation for recommendation
The goal of sequential recommendation (SR) is to predict a user's potential interested items
based on her/his historical interaction sequences. Most existing sequential recommenders …
based on her/his historical interaction sequences. Most existing sequential recommenders …
Beyond co-occurrence: Multi-modal session-based recommendation
Session-based recommendation is devoted to characterizing preferences of anonymous
users based on short sessions. Existing methods mostly focus on mining limited item co …
users based on short sessions. Existing methods mostly focus on mining limited item co …
Large multi-modal encoders for recommendation
In recent years, the rapid growth of online multimedia services, such as e-commerce
platforms, has necessitated the development of personalised recommendation approaches …
platforms, has necessitated the development of personalised recommendation approaches …
Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?
Generally, items with missing modalities are dropped in multimodal recommendation.
However, with this work, we question this procedure, highlighting that it would further …
However, with this work, we question this procedure, highlighting that it would further …
Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision
Abstract In Sequential Recommenders (SR), encoding and utilizing modalities in an end-to-
end manner is costly in terms of modality encoder sizes. Two-stage approaches can mitigate …
end manner is costly in terms of modality encoder sizes. Two-stage approaches can mitigate …