Graph Neural Networks in Recommender Systems: A Survey

@article{Wu2022GraphNN,
  title={Graph Neural Networks in Recommender Systems: A Survey},
  author={Shiwen Wu and Wentao Zhang and Fei Sun and Bin Cui},
  journal={ACM Computing Surveys (CSUR)},
  year={2022}
}
With the explosive growth of online information, recommender systems play a key role to alleviate such information overload. Due to the important application value of recommender systems, there have always been emerging works in this field. In recommender systems, the main challenge is to learn the effective user/item representations from their interactions and side information (if any). Recently, graph neural network (GNN) techniques have been widely utilized in recommender systems since most… 

Figures and Tables from this paper

Heterogeneous Graph Representation Learning for multi-target Cross-Domain Recommendation

  • Tendai Mukande
  • Computer Science
    Sixteenth ACM Conference on Recommender Systems
  • 2022
TLDR
A heterogeneous graph transformer network will be integrated to the representation learning model to prioritize the most important neighbours, and the proposed model would be able to capture complex information as well as adapt to dynamic changes in the data using matrix perturbation.

A survey on knowledge-aware news recommender systems

TLDR
This survey provides a comprehensive review of knowledge-aware news recommender systems and proposes a taxonomy that divides the models into three categories: neural methods, non-neural entity-centric methods, and non-Neural path-based methods.

Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

TLDR
A comprehensive review of the literature on graph neural network-based recommender systems, following the taxonomy above, and systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency.

Leveraging Two Types of Global Graph for Sequential Fashion Recommendation

TLDR
Two types of global graph are proposed, i.e., the user-item interaction graph and item-item transition graph, to obtain enhanced user and item representations by incorporating higher-order connections over the graphs and the graph kernel of LightGCN is adopted for information propagation in both graphs.

Graph Learning based Recommender Systems: A Review

TLDR
A systematic review of GLRS is provided, by discussing how they extract important knowledge from graph-based representations to improve the accuracy, reliability and explainability of the recommendations.

Self-supervised graph neural network with pre-training generative learning for recommendation systems

TLDR
An end-to-end graph neural network recommendation model by the interaction information based on the data characteristics of the power-law distribution is constructed and extensive experimental consistency shows that this method is effective compared to several yet competing baseline methods and further supports the development of an intelligent case assignment system with adequate performance.

Memory-Augmented Graph Neural Networks: A Neuroscience Perspective

TLDR
A systematic review of the existing works in memory-augmentation of graph neural networks from the perspective of neuroscience and psychology, which identifies the open challenges in this area and shed light on the promising directions for future work.

A Comprehensive Survey on Trustworthy Recommender Systems

WENQI FAN, The Hong Kong Polytechnic University, Hong Kong XIANGYU ZHAO∗, City University of Hong Kong, Hong Kong XIAO CHEN, The Hong Kong Polytechnic University, Hong Kong JINGRAN SU, The Hong Kong

Neural Graph Databases

TLDR
LPG2vec enables combining predictive power of the most powerful GNNs with the full scope of information encoded in the LPG model, paving the way for neural graph databases, a class of systems where the vast complexity of maintained data will benefit from modern and future graph machine learning methods.

Graph Convolution Network Recommender Rystem with Feature Embedding

  • Zhengtian Luo
  • Computer Science
    Frontiers in Computing and Intelligent Systems
  • 2022
TLDR
This work combines the use of feature information with graph convolutional network to design a new recommendation algorithm, Graph Convolution Network recommender system with Feature Embedding, GCNFE, which performs better than previous models in most cases.
...

References

SHOWING 1-10 OF 242 REFERENCES

Self-Supervised Graph Co-Training for Session-based Recommendation

TLDR
This paper combines self-supervised learning with co- training, and develops a framework to enhance session-based recommendation, which can be remarkably enhanced under the regime of self- supervised graph co-training, achieving the state-of-the-art performance.

Session-based Recommendation with Hypergraph Attention Networks

TLDR
A novel sessionbased recommendation system empowered by hypergraph attention networks effective in generating informative dynamic item embeddings and providing more accurate recommendations compared to the state-of-the-art.

Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation

TLDR
This paper models session-based data as a hypergraph and proposes a dual channel hypergraph convolutional network -- DHCN to improve SBR and innovatively integrates self-supervised learning into the training of the network by maximizing mutual information between the session representations learned via the two channels in D HCN.

Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

TLDR
A new GCN-based recommender model, Graph-Refined Convolutional Network (GRCN), which adjusts the structure of interaction graph adaptively based on status of model training, instead of remaining the fixed structure is devised.

DGTN: Dual-channel Graph Transition Network for Session-based Recommendation

TLDR
A novel method, namely Dual-channel Graph Transition Network (DGTN), to model item transitions within not only the target session but also the neighbor sessions, which demonstrates that DGTN outperforms other state-of-the-art methods.

Star Graph Neural Networks for Session-based Recommendation

TLDR
Experiments on two public benchmark datasets show that SGNN-HN can outperform state-of-the-art models in terms of P@20 and MRR@20 for session-based recommendation.

Dual Channel Hypergraph Collaborative Filtering

TLDR
A dual channel hypergraph collaborative filtering framework is proposed and a dual channel learning strategy is introduced to learn the representation of users and items so that these two types of data can be elegantly interconnected while still maintaining their specific properties.

Handling Information Loss of Graph Neural Networks for Session-based Recommendation

TLDR
A lossless encoding scheme and an edge-order preserving aggregation layer based on GRU that is dedicatedly designed to process the losslessly encoded graphs are proposed that outperforms the state-of-the-art models on three public datasets.

CKAN: Collaborative Knowledge-aware Attentive Network for Recommender Systems

TLDR
This paper proposes a novel method named Collaborative Knowledge-aware Attentive Network (CKAN), which explicitly encodes the collaborative signals by collaboration propagation and proposes a natural way of combining collaborative signals with knowledge associations together.

Disentangled Graph Collaborative Filtering

TLDR
A new model, Disentangled Graph Collaborative Filtering (DGCF), is devised to disentangle user intents and yield disentangled representations by modeling a distribution over intents for each user-item interaction, and iteratively refine the intent-aware interaction graphs and representations.
...