Decentralized Collaborative Learning Framework for Next POI Recommendation

Abstract

Next Point-of-Interest (POI) recommendation has become an indispensable functionality in Location-based Social Networks (LBSNs) due to its effectiveness in helping people decide the next POI to visit. However, accurate recommendation requires a vast amount of historical check-in data, thus threatening user privacy as the location-sensitive data needs to be handled by cloud servers. Although there have been several on-device frameworks for privacy-preserving POI recommendations, they are still resource-intensive when it comes to storage and computation, and show limited robustness to the high sparsity of user-POI interactions. On this basis, we propose a novel d ecentralized c ollaborative l earning framework for POI r ecommendation (DCLR), which allows users to train their personalized models locally in a collaborative manner. DCLR significantly reduces the local models’ dependence on the cloud for training, and can be used to expand arbitrary centralized recommendation models. To counteract the sparsity of on-device user data when learning each local model, we design two self-supervision signals to pretrain the POI representations on the server with geographical and categorical correlations of POIs. To facilitate collaborative learning, we innovatively propose to incorporate knowledge from either geographically or semantically similar users into each local model with attentive aggregation and mutual information maximization. The collaborative learning process makes use of communications between devices while requiring only minor engagement from the central server for identifying user groups, and is compatible with common privacy preservation mechanisms like differential privacy. We evaluate DCLR with two real-world datasets, where the results show that DCLR outperforms state-of-the-art on-device frameworks and yields competitive results compared with centralized counterparts.

The Structural Equation Model of the Spatial Distribution of Hydraulic Facilities on the Beijing-Hangzhou Grand Canal and its Correlation with Natural Factors

“…After validating and verifying with existing archaeological survey reports and eld investigations, a total of 1350 effective coordinate points of hydraulic engineering facilities of the Ming and Qing Dynasties were obtained. [21] Furthermore, by analyzing ancient and modern literature, the impact of natural factors such as hydrology, topography, and geomorphology on the spatial distribution of hydraulic engineering facilities along the main and tributary channels of the Grand Canal was studied. The main channel of the Grand Canal was divided into 1000 equal parts, and 1000 coordinate points along the canal were obtained to re ect the changes in hydrology and topography along the main channel.…”

Decentralized Gradient-Quantization Based Matrix Factorization for Fast Privacy-Preserving Point-of-Interest Recommendation

“…PREFER combines FL with edge learning that changes centralized server to multiple edge servers to enhance the privacy protection (Guo, Liu, Cai, Zeng, Chen, Zhou, & Xiao, 2021). DCLR introduces a two-stage training method that trains a global model using public POI data first, then distributes it to users and uses users' own data to train the final model (Long, Chen, Hung, & Yin, 2022). The most relevant existing work DMF proposes a decentralized matrix factorization framework (Chen et al, 2018) using stochastic gradient descent inspired by SVD-based decentralized matrix completion (Yun, Yu, Hsieh, Vishwanathan, & Dhillon, 2014).…”

Exploring Prior Knowledge from Human Mobility Patterns for POI Recommendation

“…X. Liu et al [23] proposed a deep convolutional auto-encoder architecture that enables the encoding layer to learn the features of different data. Some work [24][25][26] used the idea of collaborative filtering to establish the relationship between different data sources for data fusion. The fusion of multivariate data requires the algorithm to have strong scalability, but there is no general method to meet the needs.…”