# Multi-Graph Convolutional Network for Fine-Grained and Personalized POI Recommendation

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

- To the best of our knowledge, this is the first attempt to study POI recommendations using multi-view graphs. We emphasize the importance of user reviews and experiences of content in POI recommendations and integrate the features of content into POI expressions for fine-grained POI recommendations.
- We propose a new POI recommendation model Fine-grained POI Recommendation With Multi-Graph Convolutional Network (FP-MGCN). It learns a comprehensive representation of users and Fine-grained POIs by using content–content, content–POI, and POI–user relationship graphs.
- We conducted extensive experiments using two real-world datasets and the results demonstrated the advancement and effectiveness of FP-MGCN.

## 2. Related Work

#### 2.1. POI Recommendation

#### 2.2. Graph-Based Recommendation

## 3. Task Formulation

**User–POI bipartite graph.**It contains the user–POI interaction information, which is expressed as follows:$${\mathcal{G}}_{1}=\left\{\left(u,{x}_{ui},i\right)\mid u\in \mathcal{U},i\in \mathcal{I}\right\}$$**POI–content bipartite graph.**It connects POI information with content information and contains the content of items present in the POI, which is represented as follows:$${\mathcal{G}}_{2}=\left\{\left(i,{y}_{i}^{c},c\right)\mid i\in \mathcal{I},c\in C\right\}$$**Content Graph.**It shows the rich relationships between contents, containing attribute associations and descriptive contents in semantic information. Formally,$${\mathcal{G}}_{3}=\left\{\left(c,a,{c}^{*}\right)c\in C,a\in \mathcal{A},{c}^{*}\in C\right\}$$

**Input:**The heterogeneous graph $\mathcal{G}$ specifically contains three bipartite subgraphs: User–POI bipartite graph ${\mathcal{G}}_{1}$, POI–content bipartite graph ${\mathcal{G}}_{2}$, and Content Graph ${\mathcal{G}}_{3}$.

**Output:**The prediction function ${\widehat{y}}_{ui}=\mathcal{g}\left(\mathcal{G},\mathsf{\Theta}\right)$ is used to predict the probability of user interaction with the POI.

## 4. Methodology

#### 4.1. Embedding Layer

**User and POI Embedding.**Since embedding-based methods are excellent in capturing the synergistic information between user and POI, and achieve good results in POI recommendations. We choose the more popular [27,28] method for embedding, and the embedding ${p}_{u}$ and ${q}_{i}$ for user $u$ and POI $i$ as follows, respectively:

**Content Embedding.**Content is the item information contained in each POI, and users visit the POI to interact with the corresponding item, so content information is critical to users’ preferences for the selection of POIs. In real life, the content of the POI plays a decisive role in the POI node; for example, users tend to choose a restaurant for a particular dish they want to enjoy; therefore, we need to project POI content, users, and POIs into the same vector space. We define each content $c$ to correspond to an embedding vector ${r}_{c}$, so that we can obtain the content information of POI $i$ to represent a set of embedding vectors ${r}_{c}$ as ${R}_{c}$, as follows:

#### 4.2. Information Propagation

#### 4.2.1. Content–Content Propagation

**POI items.**We connect the same consumption content of users in POI; the main reason for users’ choice of POI is the consumption items in POI, which have an extremely important influence on users’ interest preference—this is the most content in the review information. For example: the user for the restaurant consumption of the main evaluation of the dish information.

**POI scenario.**The scenario situation is also an important factor for users’ POI selection. We connect POI points that have the same scenario content. Specifically, we take into account: environment, occasion (gathering, dating, etc.), consumption level, and other content.

**POI services.**By analyzing the semantic information of most reviews, we can find that the service information of POI is also as popular in the reviews, and focusing on the service information of POI can capture the fine-grained preference choices of users. For example, if a user has a high rating of the POI’s dishes but hates its slow serving speed, we can recommend a POI with higher service quality for this user by aggregating the service attribute features.

**POI Location.**This content is the basic information for POI recommendation, and POIs with the same area location are connected and aggregated in the POI content as features with a certain weight.

#### 4.2.2. Content–POI Propagation

**Content Strategic Information Construction.**For POI, we improve its representation using the content information connected by the POI–content bipartite graph ${\mathcal{G}}_{2}$. In particular, the information received by POI ${q}_{i}$ from content neighbor nodes is expressed as follows:

**POI Strategic Information Aggregation.**To obtain the fine-grained comprehensive representation of POI, we need to aggregate information from neighborhood nodes and self-expression information. Specifically, the formula is expressed as follows:

#### 4.2.3. POI–User Propagation

#### 4.3. Prediction Layer and Optimization

#### 4.4. Time Complexity Analysis

## 5. Experiments

**RQ1:**How advanced is FP-MGCN compared to other POI-recommended methods?

**RQ2:**How effective are the components of the FP-MGCN model for the results?

**RQ3:**What is the variability of performance on the model for user groups with different sparsity levels?

#### 5.1. Datasets

- Dianping (www.dianping.com): The Dianping dataset includes user information, POI, comment information, sign-in information, label information, etc. (accessed on 30 June 2022), from October 2017 to October 2019 within Nanjing.
- Yelp (https://www.yelp.com/dataset/challenge): The Yelp dataset is a very popular benchmark dataset in POI recommendations(accessed on 30 June 2022). The version we are using is from the Yelp Challenge. The Yelp data set contains user, POI, comment data, location information, and other data. This experiment used data updated before February 2020.

#### 5.2. Baselines

- BPR [33]: A representative collaborative filtering method that uses Bayesian Personalized Ranking (BPR) loss optimization matrix decomposition to recommend POIs by implicit feedback.
- FM [37]: Factorization Machine (FM) is a matrix decomposition-based recommendation algorithm that recommends items through higher-order feature crossover.
- Matapath2vec [38]: This is a meta-path recommendation method based on heterogeneous networks. The random walk is applied to solve the recommendation problem for the characteristics of heterogeneous networks.
- GC-MC [23]: A GCN-based recommendation method to update node embeddings by using GCN encoders.
- KGAT [30]: Graph modeling using a neural network framework and attention mechanisms is one of the more advanced approaches in Graph-based methods.

#### 5.3. Experiments Setup

**Evaluation Metrics.**For POI recommendation, we use Top-k recommendation, i.e., we rank the POIs that are not visited by users and recommend the k POIs with the highest scores as entries to users. To verify the sophistication of the model, we choose two evaluation metrics, recall and NDCG, to evaluate the model. For these two metrics, we take the average of all users as the report.

**Parameter Settings.**We chose TensorFlow(version:1.1.12, creator:google brain, location:San Francisco Bay Area, California) as the experimental platform for both our model and the implementation of the baseline method. We set the embedding dimension of all models to 64 in order to ensure fairness in comparison with the baseline methods. We use a grid search for hyper-parameters: the learning rate lr in the range [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.05], The learning range of the regularization parameter is [$1{e}^{-6},1{e}^{-5},1{e}^{-4},1{e}^{-3},1{e}^{-2},1{e}^{-1}$]. For the graph-based methods, we set the number of connected layers to 3 and the size of each layer to be fixed at 64. For Matapath2vec, we manually define its meta-path as user–poi–content–user. The rest of the above hyperparameters are the same as the original paper description values or the default values in the original code.

#### 5.4. Performance Comparison (RQ1)

- Our proposed FP-MGCN is ahead of the baseline methods on both datasets. The results show that the fine-grained POI representation can be obtained by the method of multiple embedding propagation layers and information propagation mechanism, and the recommendation results are more personalized by including user semantic information and POI content information.
- Compared to KGAT, one of the more advanced graph-based methods, our model performance holds some advantages. This shows the importance of the relationship between the contents of POI. It has the recommended quality improvement in the same level of computational complexity.
- Compared to the GCN-based recommended method GC-MC, the results reflect the advantage of our setting multiple propagation mechanisms. We followed the original setting and used only one convolutional layer, so GC-MC can only aggregate the information of first-order neighbors.
- Matapath2vec performs poorly compared to other baselines due to the difficulty of manually defining optimal meta-paths in graph structures with complex content.
- In the comparison of all baseline methods, KGAT performs the best, which illustrates the advantage of graph structure for complex relationship and content characterization. BPR performs the worst, indicating that simply conducting inner product between embeddings is difficult to characterize complex relationships.
- Compared to the same content metric on both datasets, the Dianping dataset has better results than Yelp. This is because the semantic information extracted from the review information in the Dianping dataset is of higher quality than Yelp, and the cut is more densely associated with the content.

#### 5.5. Study of FP-MGCN (RQ2)

#### 5.5.1. Effect of Model Depth

- Increasing the model depth can significantly improve the performance of FP-MGCN. We observe that the performance of FP-MGCN-2 and FP-MGCN-3 is significantly higher than that of FP-MGCN-1. Benefiting from second and third-order connectivity, FP-MGCN achieves optimal performance by efficiently modeling the higher-order relationships between content, POI, and user nodes.
- Continuing to increase the model depth, we can find that the performance of FP-MGCN-4 and FP-MGCN-5 decreases significantly. This indicates that an excessive number of aggregation iterations of the model can lead to overfitting phenomena and noise can interfere more with the recommendation performance.

#### 5.5.2. Effect of Aggregators in Content Graph

- The comparison shows that the performance of FP-MGCN-SUM is better than that of FP-MGCN-CON. The reason for this is that summation can superimpose feature relations better than connection.

#### 5.5.3. Effect of Aggregators for Representations

#### 5.6. User Group Experiment (RQ3)

- The experimental performance of our proposed FP-MGCN outperforms the optimal baseline method KGAT for all user groups, which indicates that FP-MGCN can mitigate the POI data sparsity problem. The reason for this is that FP-MGCN defines the content graph and utilizes its connectivity information.
- We can find that dense user groups can improve the performance of both models, which indicates that enriching the information of user–POI interactions can better capture users’ personalized preferences.

## 6. Conclusions and Future Work

## Author Contributions

## Funding

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Yang, C.; Bai, L.; Zhang, C.; Yuan, Q.; Han, J. Bridging collaborative filtering and semi-supervised learning: A neural approach for poi recommendation. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, 13–17 August 2017; pp. 1245–1254. [Google Scholar]
- Yin, H.; Wang, W.; Wang, H.; Chen, L.; Zhou, X. Spatial-aware hierarchical collaborative deep learning for POI recommendation. IEEE Trans. Knowl. Data Eng.
**2017**, 29, 2537–2551. [Google Scholar] [CrossRef] - Yu, X.; Peng, Q.; Xu, L.; Jiang, F.; Du, J.; Gong, D. A selective ensemble learning based two-sided cross-domain collaborative filtering algorithm. Inf. Process. Manag.
**2021**, 58, 102691. [Google Scholar] [CrossRef] - Cai, Z.; Yuan, G.; Qiao, S.; Qu, S.; Zhang, Y.; Bing, R. FG-CF: Friends-aware graph collaborative filtering for POI recommendation. Neurocomputing
**2022**, 488, 107–119. [Google Scholar] [CrossRef] - Lang, C.; Wang, Z.; He, K.; Sun, S. POI recommendation based on a multiple bipartite graph network model. J. Supercomput.
**2022**, 78, 9782–9816. [Google Scholar] [CrossRef] - Sun, L. POI recommendation method based on multi-source information fusion using deep learning in location-based social networks. J. Inf. Process. Syst.
**2021**, 17, 352–368. [Google Scholar] - Davtalab, M.; Alesheikh, A.A. A POI recommendation approach integrating social spatio-temporal information into probabilistic matrix factorization. Knowl. Inf. Syst.
**2021**, 63, 65–85. [Google Scholar] [CrossRef] - Xu, C.; Ding, A.S.; Zhao, K. A novel POI recommendation method based on trust relationship and spatial–temporal factors. Electron. Commer. Res. Appl.
**2021**, 48, 101060. [Google Scholar] [CrossRef] - Li, X.; Ma, D.; Ren, Y.; Luo, J.; Li, Y. Large-scale prediction of drug-protein interactions based on network information. Curr. Comput. -Aided Drug Des.
**2022**, 18, 64–72. [Google Scholar] [CrossRef] - Liu, Y.; Pei, A.; Wang, F.; Yang, Y.; Zhang, X.; Wang, H.; Dai, H.; Qi, L.; Ma, R. An attention-based category-aware GRU model for the next POI recommendation. Int. J. Intell. Syst.
**2021**, 36, 3174–3189. [Google Scholar] [CrossRef] - Zhang, S.; Tong, H.; Xu, J.; Maciejewski, R. Graph convolutional networks: A comprehensive review. Comput. Soc. Netw.
**2019**, 6, 11. [Google Scholar] [CrossRef] - Dai, S.; Yu, Y.; Fan, H.; Dong, J. Spatio-Temporal Representation Learning with Social Tie for Personalized POI Recommendation. Data Sci. Eng.
**2022**, 7, 44–56. [Google Scholar] [CrossRef] - Shi, M.; Shen, D.; Kou, Y.; Nie, T.; Yu, G. Attentional Memory Network with Correlation-based Embedding for time-aware POI recommendation. Knowl. -Based Syst.
**2021**, 214, 106747. [Google Scholar] [CrossRef] - Liu, Y.; Yang, Z.; Li, T.; Wu, D. A novel POI recommendation model based on joint spatiotemporal effects and four-way interaction. Appl. Intell.
**2022**, 52, 5310–5324. [Google Scholar] [CrossRef] - He, M.; Wen, H.; Zhang, H. LGCCF: A Linear Graph Convolutional Collaborative Filtering with Social Influence. In Proceedings of the International Conference on Database Systems for Advanced Applications, Taipei, Taiwan, 11–14 April 2021; Springer: Cham, Switzerland, 2021; pp. 306–314. [Google Scholar]
- Zhang, S.; Cheng, H. Exploiting context graph attention for poi recommendation in location-based social networks. In Proceedings of the International Conference on Database Systems for Advanced Applications, Gold Coast, QLD, Australia, 21–24 May 2018; Springer: Cham, Switzerland, 2018; pp. 83–99. [Google Scholar]
- Tang, J.; Jin, J.; Miao, Z.; Zhang, B.; An, Q.; Zhang, J. Region-aware POI Recommendation with Semantic Spatial Graph. In Proceedings of the 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD), Dalian, China, 5–7 May 2021; IEEE: New York, NY, USA, 2021; pp. 214–219. [Google Scholar]
- Fan, W.; Ma, Y.; Li, Q.; He, Y.; Zhao, E.; Tang, J.; Yin, D. Graph neural networks for social recommendation. In Proceedings of the World Wide Web Conference, San Francisco, CA, USA, 13–17 May 2019; pp. 417–426. [Google Scholar]
- Wang, W.; Zhang, W.; Liu, S.; Liu, Q.; Zhang, B.; Lin, L.; Zha, H. Beyond clicks: Modeling multi-relational item graph for session-based target behavior prediction. In Proceedings of the Web Conference 2020, Taipei, Taiwan, 20–24 April 2020; pp. 3056–3062. [Google Scholar]
- Zhou, T.; Qi, S.; Wang, W.; Shen, J.; Zhu, S.C. Cascaded parsing of human-object interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell.
**2021**, 44, 2827–2840. [Google Scholar] [CrossRef] - Zhou, T.; Li, L.; Li, X.; Feng, C.M.; Li, J.; Shao, L. Group-wise learning for weakly supervised semantic segmentation. IEEE Trans. Image Process.
**2021**, 31, 799–811. [Google Scholar] [CrossRef] - Wang, X.; He, X.; Wang, M.; Feng, F.; Chua, T.S. Neural graph collaborative filtering. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Paris, France, 21–25 July 2019; pp. 165–174. [Google Scholar]
- Berg RV, D.; Kipf, T.N.; Welling, M. Graph convolutional matrix completion. arXiv
**2017**, arXiv:1706.02263. [Google Scholar] - Zheng, Y.; Wei, P.; Chen, Z.; Cao, Y.; Lin, L. Graph-Convolved Factorization Machines for Personalized Recommendation. IEEE Trans. Knowl. Data Eng.
**2021**. [Google Scholar] [CrossRef] - Yu, D.; Shen, Y.; Xu, K.; Xu, Y. Context-Specific Point-of-Interest Recommendation Based on Popularity-Weighted Random Sampling and Factorization Machine. ISPRS Int. J. Geo-Inf.
**2021**, 10, 258. [Google Scholar] [CrossRef] - He, X.; Deng, K.; Wang, X.; Li, Y.; Zhang, Y.; Wang, M. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research And development in Information Retrieval, Virtual, 25–30 July 2020; pp. 639–648. [Google Scholar]
- Ni, J.; Huang, Z.; Cheng, J.; Gao, S. An effective recommendation model based on deep representation learning. Inf. Sci.
**2021**, 542, 324–342. [Google Scholar] [CrossRef] - Zhang, L.; Sun, Z.; Zhang, J.; Kloeden, H.; Klanner, F. Modeling hierarchical category transition for next POI recommendation with uncertain check-ins. Inf. Sci.
**2020**, 515, 169–190. [Google Scholar] [CrossRef] - Guo, W.; Su, R.; Tan, R.; Guo, H.; Zhang, Y.; Liu, Z.; Tang, R.; He, X. Dual Graph enhanced Embedding Neural Network for CTR Prediction. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore, 14–18 August 2021; pp. 496–504. [Google Scholar]
- Wang, X.; He, X.; Cao, Y.; Liu, M.; Chua, T.S. Kgat: Knowledge graph attention network for recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, 4–8 August 2019; pp. 950–958. [Google Scholar]
- Tang, X.; Yang, J.; Xiong, D.; Luo, Y.; Wang, H.; Peng, D. Knowledge-enhanced graph convolutional network for recommendation. Multimed. Tools Appl.
**2022**, 81, 28899–28916. [Google Scholar] [CrossRef] - Li, Y.; Chen, T.; Yin, H.; Huang, Z. Discovering collaborative signals for next poi recommendation with iterative seq2graph augmentation. arXiv
**2021**, arXiv:2106.15814. [Google Scholar] - Yang, X.; Zhou, P.; Wang, M. Person reidentification via structural deep metric learning. IEEE Trans. Neural Netw. Learn. Syst.
**2018**, 30, 2987–2998. [Google Scholar] [CrossRef] [PubMed] - Rendle, S.; Freudenthaler, C.; Gantner, Z.; Schmidt-Thieme, L. BPR: Bayesian personalized ranking from implicit feedback. arXiv
**2012**, arXiv:1205.2618. [Google Scholar] - Wang, H.; Zhao, M.; Xie, X.; Li, W.; Guo, M. Knowledge graph convolutional networks for recommender systems. In Proceedings of the World Wide Web Conference, San Francisco, CA, USA, 13–17 May 2019; pp. 3307–3313. [Google Scholar]
- Wang, H.; Zhang, F.; Wang, J.; Zhao, M.; Li, W.; Xie, X.; Guo, M. Ripplenet: Propagating user preferences on the knowledge graph for recommender systems. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy, 22–26 October 2018; pp. 417–426. [Google Scholar]
- Rendle, S. Factorization machines with libfm. ACM Trans. Intell. Syst. Technol. (TIST)
**2012**, 3, 1–22. [Google Scholar] [CrossRef] - Dong, Y.; Chawla, N.V.; Swami, A. metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, 13–17 August 2017; pp. 135–144. [Google Scholar]

**Figure 1.**User record graph of POI recommendation scenarios. It contains three layers: user layer, POI layer and content layer, and the icons of each layer represent different nodes.

Dataset | #Users | #POIs | #Check-Ins | Density |
---|---|---|---|---|

Dianping | 17,649 | 12,872 | 362,680 | 0.1627% |

Yelp | 30,595 | 18,496 | 783,291 | 0.1902% |

Methods | Dianping | Yelp | ||
---|---|---|---|---|

Recall@10 | NDCG@10 | Recall@10 | NDCG@10 | |

BPR | 0.0762 | 0.0513 | 0.0355 | 0.0445 |

FM | 0.0801 | 0.0635 | 0.0416 | 0.0463 |

Matapath2vec | 0.0724 | 0.0472 | 0.0321 | 0.0362 |

GC-MC | 0.0821 | 0.0658 | 0.0425 | 0.0472 |

KGAT | 0.0862 | 0.0688 | 0.0451 | 0.0485 |

FP-MGCN | 0.0914 | 0.0711 | 0.0476 | 0.0518 |

Dianping | Yelp | |||
---|---|---|---|---|

Recall@10 | NDCG@10 | Recall@10 | NDCG@10 | |

FP-MGCN-1 | 0.0865 | 0.0672 | 0.0455 | 0.0506 |

FP-MGCN-2 | 0.0906 | 0.0716 | 0.0468 | 0.0512 |

FP-MGCN-3 | 0.0914 | 0.0711 | 0.0476 | 0.0518 |

FP-MGCN-4 | 0.0887 | 0.0698 | 0.0462 | 0.0508 |

FP-MGCN-5 | 0.0796 | 0.0655 | 0.0443 | 0.0498 |

Dianping | Yelp | |||
---|---|---|---|---|

Recall@10 | NDCG@10 | Recall@10 | NDCG@10 | |

FP-MGCN-CON | 0.0899 | 0.0701 | 0.0464 | 0.0502 |

FP-MGCN-SUM | 0.0914 | 0.0711 | 0.0476 | 0.0518 |

Dianping | Yelp | |||
---|---|---|---|---|

Recall@10 | NDCG@10 | Recall@10 | NDCG@10 | |

FP-MGCN-GCN | 0.0882 | 0.0667 | 0.0449 | 0.0477 |

FP-MGCN-BI | 0.0914 | 0.0711 | 0.0476 | 0.0518 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Zhang, S.; Bai, Z.; Li, P.; Chang, Y.
Multi-Graph Convolutional Network for Fine-Grained and Personalized POI Recommendation. *Electronics* **2022**, *11*, 2966.
https://doi.org/10.3390/electronics11182966

**AMA Style**

Zhang S, Bai Z, Li P, Chang Y.
Multi-Graph Convolutional Network for Fine-Grained and Personalized POI Recommendation. *Electronics*. 2022; 11(18):2966.
https://doi.org/10.3390/electronics11182966

**Chicago/Turabian Style**

Zhang, Suzhi, Zijian Bai, Pu Li, and Yuanyuan Chang.
2022. "Multi-Graph Convolutional Network for Fine-Grained and Personalized POI Recommendation" *Electronics* 11, no. 18: 2966.
https://doi.org/10.3390/electronics11182966