DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation

TL;DR

DisenPOI introduces a novel framework that disentangles sequential and geographical influences in POI recommendation using dual graphs and contrastive learning, improving recommendation accuracy and interpretability.

Contribution

The paper proposes a dual-graph, self-supervised framework that effectively separates sequential and geographical influences in POI recommendation, enhancing performance and interpretability.

Findings

Outperforms existing methods on three datasets

Effectively disentangles influences with contrastive learning

Improves recommendation accuracy and interpretability

Abstract

Point-of-Interest (POI) recommendation plays a vital role in various location-aware services. It has been observed that POI recommendation is driven by both sequential and geographical influences. However, since there is no annotated label of the dominant influence during recommendation, existing methods tend to entangle these two influences, which may lead to sub-optimal recommendation performance and poor interpretability. In this paper, we address the above challenge by proposing DisenPOI, a novel Disentangled dual-graph framework for POI recommendation, which jointly utilizes sequential and geographical relationships on two separate graphs and disentangles the two influences with self-supervision. The key novelty of our model compared with existing approaches is to extract disentangled representations of both sequential and geographical influences with contrastive learning. To be specific, we construct a geographical graph and a sequential graph based on the check-in sequence of a user. We tailor their propagation schemes to become sequence-/geo-aware to better capture the corresponding influences. Preference proxies are extracted from check-in sequence as pseudo labels for the two influences, which supervise the disentanglement via a contrastive loss. Extensive experiments on three datasets demonstrate the superiority of the proposed model.