cs.LGNov 4, 2026

Alternatives to Shallow Autoencoders for Collaborative Filtering

Authors: Mario Mallea, Angela Nebot, Francisco Mugica

Organizations: Universitat Politècnica de Catalunya, Soft Computing Research Group at the Intelligent Data Science and Artificial Intelligence Research Center, Barcelona, Spain

Abstract

Collaborative filtering (CF) is a cornerstone of recommender systems and plays a relevant role in many modern applications. CF uses user-item interaction data to discover future preferences. Although deep learning models have shown promise in CF, Embarrassingly Shallow Autoencoders for Sparse Data (EASE) has gained attention for its outstanding ranking accuracy provided by its closed-form solution. EASE relies primarily on relationships among items to fit a full-rank high-dimensional linear mapping. We hypothesize that this design limits its capacity to capture similar but not equivalent fine-grained user relationships, consequently limiting its recommendation accuracy. This paper introduces an alternative formulation based on EASE that takes advantage of user-user information. Furthermore, we propose a hybrid model that combines both user-user and item-item adjacency distributions. Our experiments reveal that the proposed models outperform EASE on well-known recommendation benchmarks, highlighting the significance of including the user alternative in shallow autoencoder studies for CF.

Explore similar work

CardsList
  1. Collaborative Filtering Through Weighted Similarities of User and Item Embeddings

    Apr 16, 2026Pedro R. Pires, Rafael T. Sereicikas, Gregorio F. Azevedo +1Ensemble LearningRecommender Systems

  2. RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation

    Mar 17, 2026Yixuan Huang, Jiawei Chen, Shengfan Zhang +1Graph Contrastive LearningCollaborative Filtering

  3. A Counterfactual Approach for Addressing Individual User Unfairness in Collaborative Recommender System

    Feb 24, 2026Nikita Baidya, Bidyut Kr. Patra, Ratnakar DashFairness in Recommender SystemsRecommender Systems