HGCF: Hyperbolic Graph Convolution Networks for Collaborative Filtering

Sun, Junhua; Cheng, Zhaoyue; Zuberi, Saba; Pérez, Felipe; Volkovs, Maksims

doi:10.1145/3442381.3450101

Cited by 87 publications

(70 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HME [8] studies the joint interactions of multi-view information in hyperbolic space for next-poi recommendation. HGCF [37] captures higher-order information in user-item interactions by incorporating multiple levels of neighborhood aggregation through a tangential hyperbolic GCN module. LKGR [5] presents a knowledge-aware attention mechanism for hyperbolic recommender systems.…”

Section: Hyperbolic Recommender Systemsmentioning

confidence: 99%

“…The basic idea of graph neural collaborative filtering [5,13,37,43] is to learn representation for nodes by extracting the highorder interactions via the message aggregation. Similar to Euclidean graph neural collaborative filtering, there are three components in hyperbolic settings: (1) hyperbolic embedding initializing layer; (2) hyperbolic message aggregation; (3) hyperbolic prediction layer.…”

Section: (Hyperbolic) Graph Neural Collaborative Filteringmentioning

confidence: 99%

See 1 more Smart Citation

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

Yang

Zhou

Liu

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

In large-scale recommender systems, the user-item networks are generally scale-free or expand exponentially. The latent features (also known as embeddings) used to describe the user and item are determined by how well the embedding space fits the data distribution. Hyperbolic space offers a spacious room to learn embeddings with its negative curvature and metric properties, which can well fit data with tree-like structures. Recently, several hyperbolic approaches have been proposed to learn high-quality representations for the users and items. However, most of them concentrate on developing the hyperbolic similitude by designing appropriate projection operations, whereas many advantageous and exciting geometric properties of hyperbolic space have not been explicitly explored. For example, one of the most notable properties of hyperbolic space is that its capacity space increases exponentially with the radius, which indicates the area far away from the hyperbolic origin is much more embeddable. Regarding the geometric properties of hyperbolic space, we bring up a Hyperbolic Regularization powered Collaborative Filtering (HRCF) and design a geometric-aware hyperbolic regularizer. Specifically, the proposal boosts optimization procedure via the root alignment and origin-aware penalty, which is simple yet impressively effective. Through theoretical analysis, we further show that our proposal is able to tackle the over-smoothing problem caused by hyperbolic aggregation and also brings the models a better discriminative ability. We conduct extensive empirical analysis, comparing our proposal against a large set of baselines on several public benchmarks. The empirical results show that our approach achieves highly competitive performance and surpasses both the leading Euclidean and hyperbolic baselines by considerable margins. Further analysis verifies the rationality and effectiveness of the proposal for robust, deeper, and lightweight neural graph collaborative filtering.

show abstract

Section: Hyperbolic Recommender Systemsmentioning

confidence: 99%

Section: (Hyperbolic) Graph Neural Collaborative Filteringmentioning

confidence: 99%

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

Yang

Zhou

Liu

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

show abstract

“…For example, learning disentangled or behavior-aware user representations is proposed to improve CF paradigm, e.g., DGCF [36], MacridVAE [24] and MBGMN [41]. The hyperbolic embedding space is adopted to encode high-order information from neighboring users/items in [32].…”

Section: Graph-based Recommender Systemsmentioning

confidence: 99%

Hypergraph Contrastive Collaborative Filtering

Xia,

Huang,

et al. 2022

Preprint

View full text Add to dashboard Cite

Collaborative Filtering (CF) has emerged as fundamental paradigms for parameterizing users and items into latent representation space, with their correlative patterns from interaction data. Among various CF techniques, the development of GNN-based recommender systems, e.g., PinSage and LightGCN, has offered the state-of-theart performance. However, two key challenges have not been well explored in existing solutions: i) The over-smoothing effect with deeper graph-based CF architecture, may cause the indistinguishable user representations and degradation of recommendation results. ii) The supervision signals (i.e., user-item interactions) are usually scarce and skewed distributed in reality, which limits the representation power of CF paradigms. To tackle these challenges, we propose a new self-supervised recommendation framework Hypergraph Contrastive Collaborative Filtering (HCCF) to jointly capture local and global collaborative relations with a hypergraphenhanced cross-view contrastive learning architecture. In particular, the designed hypergraph structure learning enhances the discrimination ability of GNN-based CF paradigm, so as to comprehensively capture the complex high-order dependencies among users. Additionally, our HCCF model effectively integrates the hypergraph structure encoding with self-supervised learning to reinforce the representation quality of recommender systems, based on the hypergraph-enhanced self-discrimination. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods, and the robustness against sparse user interaction data. Our model implementation codes are available at https://github.com/akaxlh/HCCF.

show abstract

“…Their flexibility (in particular, the curvature of the space) have been successfully leveraged in various areas such as computer vision, NLP, and computational biology. In the context of social networks, they are currently used in collaborative filtering where the goal is to use past user-item/advertisement interactions to build the recommender systems (see, for example, [221] 13 ).…”

Section: Hyperbolic Spacesmentioning

confidence: 99%