Privacy Preserving Inference of Personalized Content for Out of Matrix Users

• URL: http://arxiv.org/abs/2508.14905v1
• Date: Tue, 12 Aug 2025 02:55:29 GMT
• Title: Privacy Preserving Inference of Personalized Content for Out of Matrix Users
• Authors: Michael Sun, Tai Vu, Andrew Wang,
• Abstract summary: DeepNaniNet is a deep neural recommendation framework that combines user-item interactions, item-item relations, and rich textual review embeddings derived from BERT.<n>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.<n>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 Anime
• Score: 2.6817508430601924
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Vectorized Context-Aware Embeddings for GAT-Based Collaborative Filtering [0.0]
  This paper presents a Graph Attention Network (GAT) based Collaborative Filtering framework enhanced with Large Language Model (LLM) driven context aware embeddings.<n>Experiments on the MovieLens 100k and 1M datasets show consistent improvements over state-of-the-art baselines in Precision, NDCG, and MAP.<n>Our approach effectively mitigates sparsity and cold-start limitations by integrating LLM-derived contextual understanding into graph-based architectures.
  arXiv  Detail & Related papers  (2025-10-30T13:07:39Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users [111.56469697145519]
  We propose Few-Shot Preference Optimization, which reframes reward modeling as a meta-learning problem.<n>Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them.<n>We generate over 1M synthetic personalized preferences using publicly available LLMs.<n>We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study.
  arXiv  Detail & Related papers  (2025-02-26T17:08:46Z)
• A Hybrid Filtering for Micro-video Hashtag Recommendation using Graph-based Deep Neural Network [0.3573481101204926]
  We propose a hybrid filtering based MIcro-video haSHtag recommendatiON MISHON technique to recommend hashtags for microvideos. Since hashtags reflect users topical interests, we find similar users based on historical tagging behavior to model user relatedness. We also propose a content and social influence based technique to model the relatedness of cold start users with influential users.
  arXiv  Detail & Related papers  (2024-10-14T10:46:32Z)
• Firzen: Firing Strict Cold-Start Items with Frozen Heterogeneous and Homogeneous Graphs for Recommendation [34.414081170244955]
  We propose a unified framework incorporating multi-modal content of items and knowledge graphs (KGs) to solve both strict cold-start and warm-start recommendation. Our model yields significant improvements for strict cold-start recommendation and outperforms or matches the state-of-the-art performance in the warm-start scenario.
  arXiv  Detail & Related papers  (2024-10-10T06:48:27Z)
• Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation [45.39171059168941]
  heterogeneous information network (HIN) is a potent tool for mitigating data sparsity in recommender systems. In this paper, we suggest the HIN is partitioned into private HINs stored on the client side and shared HINs on the server. We formalize the privacy definition for HIN-based federated recommendation (FedRec) in the light of differential privacy.
  arXiv  Detail & Related papers  (2023-10-18T05:59:41Z)
• Federated Social Recommendation with Graph Neural Network [69.36135187771929]
  We propose fusing social information with user-item interactions to alleviate it, which is the social recommendation problem. We devise a novel framework textbfFedrated textbfSocial recommendation with textbfGraph neural network (FeSoG)
  arXiv  Detail & Related papers  (2021-11-21T09:41:39Z)
• Learning to Learn a Cold-start Sequential Recommender [70.5692886883067]
  The cold-start recommendation is an urgent problem in contemporary online applications. We propose a meta-learning based cold-start sequential recommendation framework called metaCSR. metaCSR holds the ability to learn the common patterns from regular users' behaviors.
  arXiv  Detail & Related papers  (2021-10-18T08:11:24Z)
• Stronger Privacy for Federated Collaborative Filtering with Implicit Feedback [13.37601438005323]
  We propose a practical federated recommender system for implicit data under user-level local differential privacy (LDP) The privacy-utility trade-off is controlled by parameters $epsilon$ and $k$, regulating the per-update privacy budget and the number of $epsilon$-LDP gradient updates sent by each user respectively. We empirically demonstrate the effectiveness of our framework on the MovieLens dataset, achieving up to Hit Ratio with K=10 (HR@10) 0.68 on 50k users with 5k items.
  arXiv  Detail & Related papers  (2021-05-09T13:41:45Z)
• Joint Training Capsule Network for Cold Start Recommendation [64.35879555545749]
  This paper proposes a novel neural network, joint training capsule network (JTCN) for the cold start recommendation task. An attentive capsule layer is proposed to aggregate high-level user preference from the low-level interaction history. Experiments on two publicly available datasets demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2020-05-23T04:27:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.