Privacy Preserving Inference of Personalized Content for Out of Matrix Users

TL;DR

DeepNaniNet is a novel deep neural recommendation framework that effectively handles cold start and privacy constraints by leveraging graph-based architectures and rich textual embeddings, achieving state-of-the-art results on new and existing datasets.

Contribution

We introduce DeepNaniNet, a new inductive graph-based recommendation model that enables privacy-preserving, high-quality recommendations for cold start and out-of-matrix users using content baskets and rich textual embeddings.

Findings

DeepNaniNet achieves state-of-the-art cold start results on CiteULike.

It matches DropoutNet in user recall for out-of-matrix users.

Outperforms WMF and DropoutNet on AnimeULike warm start by up to 7x and 1.5x in Recall@100.

Abstract

Recommender systems for niche and dynamic communities face persistent challenges from data sparsity, cold start users and items, and privacy constraints. Traditional collaborative filtering and content-based approaches underperform in these settings, either requiring invasive user data or failing when preference histories are absent. We present DeepNaniNet, a deep neural recommendation framework that addresses these challenges through an inductive graph-based architecture combining user-item interactions, item-item relations, and rich textual review embeddings derived from BERT. Our design enables cold start recommendations without profile mining, using a novel "content basket" user representation and an autoencoder-based generalization strategy for unseen users. We introduce AnimeULike, a new dataset of 10,000 anime titles and 13,000 users, to evaluate performance in realistic scenarios with high proportions of guest or low-activity users. DeepNaniNet achieves state-of-the-art cold start results on the CiteULike benchmark, matches DropoutNet in user recall without performance degradation for out-of-matrix users, and outperforms Weighted Matrix Factorization (WMF) and DropoutNet on AnimeULike warm start by up to 7x and 1.5x in Recall@100, respectively. Our findings demonstrate that DeepNaniNet delivers high-quality, privacy-preserving recommendations in data-sparse, cold start-heavy environments while effectively integrating heterogeneous content sources.