Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2026

Abstract

Shallow autoencoders are appealing recommenders due to their simplicity, scalability, and competitive retrieval quality, but they struggle in strict cold-start settings where new items have no interactions. We propose an inductive shallow autoencoder that leverages item side information (language embeddings) by fixing the decoder to item features and learning only an encoder in the same semantic space. To prevent trivial self-reconstruction without enforcing a hard zero diagonal, we introduce diagonal gating: a leave-one-item-out objective that blocks the self-copy shortcut only for the item being updated while retaining context from the rest of the user history. An alternating-style optimization trains the model. Experiments on three real-world benchmarks show consistent gains over strong cold-start baselines, including other shallow autoencoders, and support lightweight (cross-domain) semantic user modeling.

Keywords

Cold-start Recommenders, Language Models, Shallow Methods

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

UMAP '26: Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization, Gothenburg, Sweden, June 8-11

First Page

398

Last Page

402

ISBN

9798400723117

Identifier

10.1145/3774935.3806192

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3774935.3806192

Download

Share

COinS