Unifying Inductive, Cross-Domain, and Multimodal Learning for Robust and Generalizable Recommendation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chung, Chanyoung, Lee, Kyeongryul, Park, Sunbin, Whang, Joyce Jiyoung
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912669714350080
author Chung, Chanyoung
Lee, Kyeongryul
Park, Sunbin
Whang, Joyce Jiyoung
author_facet Chung, Chanyoung
Lee, Kyeongryul
Park, Sunbin
Whang, Joyce Jiyoung
contents Recommender systems have long been built upon the modeling of interactions between users and items, while recent studies have sought to broaden this paradigm by generalizing to new users and items, incorporating diverse information sources, and transferring knowledge across domains. Nevertheless, these efforts have largely focused on individual aspects, hindering their ability to tackle the complex recommendation scenarios that arise in daily consumptions across diverse domains. In this paper, we present MICRec, a unified framework that fuses inductive modeling, multimodal guidance, and cross-domain transfer to capture user contexts and latent preferences in heterogeneous and incomplete real-world data. Moving beyond the inductive backbone of INMO, our model refines expressive representations through modality-based aggregation and alleviates data sparsity by leveraging overlapping users as anchors across domains, thereby enabling robust and generalizable recommendation. Experiments show that MICRec outperforms 12 baselines, with notable gains in domains with limited training data.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21812
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unifying Inductive, Cross-Domain, and Multimodal Learning for Robust and Generalizable Recommendation
Chung, Chanyoung
Lee, Kyeongryul
Park, Sunbin
Whang, Joyce Jiyoung
Information Retrieval
Artificial Intelligence
Machine Learning
Recommender systems have long been built upon the modeling of interactions between users and items, while recent studies have sought to broaden this paradigm by generalizing to new users and items, incorporating diverse information sources, and transferring knowledge across domains. Nevertheless, these efforts have largely focused on individual aspects, hindering their ability to tackle the complex recommendation scenarios that arise in daily consumptions across diverse domains. In this paper, we present MICRec, a unified framework that fuses inductive modeling, multimodal guidance, and cross-domain transfer to capture user contexts and latent preferences in heterogeneous and incomplete real-world data. Moving beyond the inductive backbone of INMO, our model refines expressive representations through modality-based aggregation and alleviates data sparsity by leveraging overlapping users as anchors across domains, thereby enabling robust and generalizable recommendation. Experiments show that MICRec outperforms 12 baselines, with notable gains in domains with limited training data.
title Unifying Inductive, Cross-Domain, and Multimodal Learning for Robust and Generalizable Recommendation
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.21812