paper-with-me

Papers

Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations

2025-08-16 · Viacheslav Yusupov, Maxim Rakhuba, Evgeny Frolov arxiv

Recent studies have demonstrated the potential of hyperbolic geometry for capturing complex patterns from interaction data in recommender systems. In this work, we introduce a novel hyperbolic recommendation model that uses geometrical insights to improve representation learning and increase computational stability at the same time. We reformulate the notion of hyperbolic distances to unlock additional representation capacity over conventional Euclidean space and learn more expressive user and item representations. To better capture user-items interactions, we construct a triplet loss that models ternary relations between users and their corresponding preferred and nonpreferred choices through a mix of pairwise interaction terms driven by the geometry of data. Our hyperbolic approach not only outperforms existing Euclidean and hyperbolic models but also reduces popularity bias, leading to more diverse and personalized recommendations.

📄 PDF Abstract BibTeX arXiv:2508.11978

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images

2024-12-12 · Wenrui Li, Zhe Yang, Wei Han, Hengyu Man 외

Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low cost and accurate results. However, singl…

3D Point Cloud Reconstruction3D ReconstructionPoint cloud reconstructionTriplet

Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks

2025-11-17 · Minsoo Jo, Dongyoon Yang, Taesup Kim arxiv

Adversarial examples in neural networks have been extensively studied in Euclidean geometry, but recent advances in \textit{hyperbolic networks} call for a reevaluation of attack strategies in non-Euclidean geometries. E…

Cross-Modal RetrievalImage ClassificationAdversarial Attack

Learning to Fuse Local Geometric Features for 3D Rigid Data Matching

2019-04-27 · Jiaqi Yang, Chen Zhao, Ke Xian, Angfan Zhu 외

This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common practice to generate distinctive geometric de…

Triplet

A group-theoretic framework for machine learning in hyperbolic spaces

2025-01-12 · Vladimir Jaćimović

Embedding the data in hyperbolic spaces can preserve complex relationships in very few dimensions, thus enabling compact models and improving efficiency of machine learning (ML) algorithms. The underlying idea is that hy…

Learning Hyperbolic Representations for Unsupervised 3D Segmentation

2020-09-28 · Joy Hsu, Jeffrey Gu, Gong Her Wu, Wah Chiu 외

There exists a need for unsupervised 3D segmentation on complex volumetric data, particularly when annotation ability is limited or discovery of new categories is desired. Using the observation that much of 3D volumetric…

SegmentationTriplet