Shallow AutoEncoding Recommender with Cold Start Handling via Side Features

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cui, Edward DongBo, Zhang, Lu, Lee, William Ping-hsun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908364093521920
author Cui, Edward DongBo
Zhang, Lu
Lee, William Ping-hsun
author_facet Cui, Edward DongBo
Zhang, Lu
Lee, William Ping-hsun
contents User and item cold starts present significant challenges in industrial applications of recommendation systems. Supplementing user-item interaction data with metadata is a common solution-but often at the cost of introducing additional biases. In this work, we introduce an augmented EASE model that seamlessly integrates both user and item side information to address these cold start issues. Our straightforward, autoencoder-based method produces a closed-form solution that leverages rich content signals for cold items while refining user representations in data-sparse environments. Importantly, our method strikes a balance by effectively recommending cold start items and handling cold start users without incurring extra bias, and it maintains strong performance in warm settings. Experimental results demonstrate improved recommendation accuracy and robustness compared to previous collaborative filtering approaches. Moreover, our model serves as a strong baseline for future comparative studies.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02288
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Shallow AutoEncoding Recommender with Cold Start Handling via Side Features
Cui, Edward DongBo
Zhang, Lu
Lee, William Ping-hsun
Information Retrieval
Machine Learning
User and item cold starts present significant challenges in industrial applications of recommendation systems. Supplementing user-item interaction data with metadata is a common solution-but often at the cost of introducing additional biases. In this work, we introduce an augmented EASE model that seamlessly integrates both user and item side information to address these cold start issues. Our straightforward, autoencoder-based method produces a closed-form solution that leverages rich content signals for cold items while refining user representations in data-sparse environments. Importantly, our method strikes a balance by effectively recommending cold start items and handling cold start users without incurring extra bias, and it maintains strong performance in warm settings. Experimental results demonstrate improved recommendation accuracy and robustness compared to previous collaborative filtering approaches. Moreover, our model serves as a strong baseline for future comparative studies.
title Shallow AutoEncoding Recommender with Cold Start Handling via Side Features
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2504.02288