# AdaptGOT: A Pre-trained Model for Adaptive Contextual POI Representation Learning

arXiv: https://arxiv.org/abs/2506.21612 · HTML: https://mlsanity.com/paper/2506.21612/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness](https://mlsanity.com/paper/2110.03753/) (2021)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation](https://mlsanity.com/paper/2303.04741/) (2023)
- [Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks](https://mlsanity.com/paper/2006.13866/) (2020)
- [Interest-aware Message-Passing GCN for Recommendation](https://mlsanity.com/paper/2102.10044/) (2021)
- [SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation](https://mlsanity.com/paper/2210.12213/) (2022)
- [Context-Aware Attention-Based Data Augmentation for POI Recommendation](https://mlsanity.com/paper/2106.15984/) (2021)
- [Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems](https://mlsanity.com/paper/2208.08847/) (2022)
- [SUGER: A Subgraph-based Graph Convolutional Network Method for Bundle Recommendation](https://mlsanity.com/paper/2205.11231/) (2022)
- [M3PT: A Multi-Modal Model for POI Tagging](https://mlsanity.com/paper/2306.10079/) (2023)
- [ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation](https://mlsanity.com/paper/2407.07912/) (2024)

## Built on by (most cited first, 1 of 1)

- [VisitHGNN: Heterogeneous Graph Neural Networks for Modeling Point-of-Interest Visit Patterns](https://mlsanity.com/paper/2510.02702/) (2025)

## Abstract (arXiv)

Currently, considerable strides have been achieved in Point-of-Interest (POI) embedding methodologies, driven by the emergence of novel POI tasks like recommendation and classification. Despite the success of task-specific, end-to-end models in POI embedding, several challenges remain. These include the need for more effective multi-context sampling strategies, insufficient exploration of multiple POI contexts, limited versatility, and inadequate generalization. To address these issues, we propose the AdaptGOT model, which integrates both the (Adapt)ive representation learning technique and the Geographical-Co-Occurrence-Text (GOT) representation with a particular emphasis on Geographical location, Co-Occurrence and Textual information. The AdaptGOT model comprises three key components: (1) contextual neighborhood generation, which integrates advanced mixed sampling techniques such as KNN, density-based, importance-based, and category-aware strategies to capture complex contextual neighborhoods; (2) an advanced GOT representation enhanced by an attention mechanism, designed to derive high-quality, customized representations and efficiently capture complex interrelations between POIs; and (3) the MoE-based adaptive encoder-decoder architecture, which ensures topological consistency and enriches contextual representation by minimizing Jensen-Shannon divergence across varying contexts. Experiments on two real-world datasets and multiple POI tasks substantiate the superior performance of the proposed AdaptGOT model.