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

TL;DR

AdaptGOT introduces a novel adaptive POI embedding model that combines geographical, co-occurrence, and textual data with advanced sampling and attention mechanisms to improve contextual representation and generalization in POI tasks.

Contribution

The paper presents AdaptGOT, a new model integrating adaptive learning, multi-context sampling, and an enhanced GOT representation with attention, addressing limitations of previous POI embedding methods.

Findings

Outperforms existing POI embedding models on real-world datasets.

Effectively captures complex POI relationships using advanced sampling and attention.

Enhances generalization across multiple POI tasks.

Abstract

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.