# Kernel-based Substructure Exploration for Next POI Recommendation

arXiv: https://arxiv.org/abs/2210.03969 · HTML: https://mlsanity.com/paper/2210.03969/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 8 Oct 2022.

## Builds on (most cited first, 12 of 12)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [KerGNNs: Interpretable Graph Neural Networks with Graph Kernels](https://mlsanity.com/paper/2201.00491/) (2022)
- [KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification](https://mlsanity.com/paper/2205.10550/) (2022)
- [Dynamic Sequential Graph Learning for Click-Through Rate Prediction](https://mlsanity.com/paper/2109.12541/) (2021)

## Built on by (most cited first, 8 of 8)

- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [A Diffusion model for POI recommendation](https://mlsanity.com/paper/2304.07041/) (2023)
- [Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting](https://mlsanity.com/paper/2309.12028/) (2023)
- [ALEX: Towards Effective Graph Transfer Learning with Noisy Labels](https://mlsanity.com/paper/2309.14673/) (2023)
- [DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation](https://mlsanity.com/paper/2210.16591/) (2022)
- [Redundancy-Free Self-Supervised Relational Learning for Graph Clustering](https://mlsanity.com/paper/2309.04694/) (2023)
- [RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classification](https://mlsanity.com/paper/2308.02335/) (2023)
- [NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration](https://mlsanity.com/paper/2505.15180/) (2025)

## Abstract (arXiv)

Point-of-Interest (POI) recommendation, which benefits from the proliferation of GPS-enabled devices and location-based social networks (LBSNs), plays an increasingly important role in recommender systems. It aims to provide users with the convenience to discover their interested places to visit based on previous visits and current status. Most existing methods usually merely leverage recurrent neural networks (RNNs) to explore sequential influences for recommendation. Despite the effectiveness, these methods not only neglect topological geographical influences among POIs, but also fail to model high-order sequential substructures. To tackle the above issues, we propose a Kernel-Based Graph Neural Network (KBGNN) for next POI recommendation, which combines the characteristics of both geographical and sequential influences in a collaborative way. KBGNN consists of a geographical module and a sequential module. On the one hand, we construct a geographical graph and leverage a message passing neural network to capture the topological geographical influences. On the other hand, we explore high-order sequential substructures in the user-aware sequential graph using a graph kernel neural network to capture user preferences. Finally, a consistency learning framework is introduced to jointly incorporate geographical and sequential information extracted from two separate graphs. In this way, the two modules effectively exchange knowledge to mutually enhance each other. Extensive experiments conducted on two real-world LBSN datasets demonstrate the superior performance of our proposed method over the state-of-the-arts. Our codes are available at https://github.com/Fang6ang/KBGNN.