Differential Privacy-Based Social Network Detection Over Spatio-Temporal Proximity for Secure POI Recommendation

Acharya, Malika; Mohbey, Krishna Kumar

doi:10.1007/s42979-023-01683-7

Cited by 13 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the CSRLP could aid in selecting sites for healthcare facilities by considering the mobility patterns of disabled individuals [74]. Additionally, integrating CSRLP with predictive analytics of Point-of-Interest (POI) data on young people's travel behaviors could facilitate the establishment of youthoriented amenities, such as cinemas and restaurants, in their preferred areas [75][76][77].…”

Section: Discussionmentioning

confidence: 99%

Locating Senior-Friendly Restaurants in a Community: A Bi-Objective Optimization Approach for Enhanced Equality and Convenience

Yang,

Li,

2024

IJGI

View full text Add to dashboard Cite

Senior-friendly restaurants are dining establishments that cater specifically to the needs and preferences of older adults in a community. As the physical capabilities of seniors progressively decline and their activity spaces contract over time, determining optimal locations for such restaurants to ensure their accessibility becomes crucial. Nevertheless, the criteria for the location selection of senior-friendly restaurants are multifaceted, necessitating the consideration of both equality and convenience. First, these restaurants often receive government funding, which means that equitable access should be guaranteed for all community residents. Second, the daily activity patterns of seniors should be accounted for. Therefore, these restaurants should be situated in close proximity to other essential facilities utilized by seniors, such as recreational facilities that accommodate routine postmeal activities. Despite the long-standing application of spatial optimization approaches to facility location issues, no existing models directly address the location selection of senior-friendly restaurants. This study introduces a bi-objective optimization model, the Community Senior-Friendly Restaurants Location Problem (CSRLP), designed to determine optimal locations for senior-friendly restaurants, taking into consideration both service coverage and proximity to recreational facilities simultaneously. We formulated the CSRLP as an integer linear programming model. Simulation tests indicate that the CSRLP can be solved both effectively and efficiently. Applying the CSRLP model to two communities in Dongcheng District, Beijing, China, we explored Pareto optimal solutions, facilitating the selection of senior-friendly restaurant locations under diverse scenarios. The results highlight the significant value of spatial optimization in aiding senior-friendly restaurant location planning and underscore key policy implications.

show abstract

Section: Discussionmentioning

confidence: 99%

Locating Senior-Friendly Restaurants in a Community: A Bi-Objective Optimization Approach for Enhanced Equality and Convenience

Yang,

Li,

2024

IJGI

View full text Add to dashboard Cite

show abstract

“…Privacy is also one of the major concerns in recommendation tasks. Acharya et al [26] proposed the DPSND-Rec method that protected privacy using Laplacian noise and exploited the spatiotemporal neighbors for social linkage mining. The social links were mined based on spatiotemporal similarity using similarity indices.…”

Section: Related Workmentioning

confidence: 99%

Long-Term Preference Mining With Temporal and Spatial Fusion for Point-of-Interest Recommendation

Acharya,

Mohbey,

Rajput

2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

The growth of the tourism industry has greatly boosted the Point-of-Interest (POI) recommendation tasks using Location-based Social Networks (LBSNs). The ever-evolving nature of user preferences poses a major problem. To address this, we propose a Long-term Preference Mining (LTPM) approach that utilizes the temporal recency (TR) measure in the visits along with the location-aware recommendation based on spatial proximity (SP) to the user's location. The temporal dynamics and changing preferences are exploited based on the modified Long Short-term Memory (LSTM) that utilizes the time decay. The spatial considerations are modeled in two aspects: geographical proximity based on enhanced representation learning using orthogonal mapping. Second, the Region-of-Interest (ROI) is based on spatial griding and metric learning to capture the spatial relationships between POIs to enhance the metric space representation. The final recommendations are based on a multi-head attention mechanism that allocates the weights to different features. The combination of three models, called, LTPM-TRSP approach captures the user-POI, POI-POI, and POI-time relationships by focusing on the informative representation of sequential and spatial data. The category-aware final recommendations based on comprehensive historical behavior and geographical context are quite efficacious. The experimentation on three real-world datasets, Gowalla, Foursquare, and Weeplaces, also suggests the potency compared to other state-of-the-art approaches.

show abstract

“…For all these baselines, we followed the default hyper-parameter settings as stated in their papers. Note that, since our datasets do not have auxiliary information such as social relationships or user attributes, we did not use the methods from [10,11,25,26] that utilize the aforementioned auxiliary information as baselines. In addition, since we focused on the classical POI recommendation task, we did not choose GNN models for the next POI recommendation [27,28] or tour the recommendations [29] as baselines.…”

Section: Mf-based Gnn-based Gnn and Ssl-basedmentioning

confidence: 99%

Self-Supervised Spatio-Temporal Graph Learning for Point-of-Interest Recommendation

Liu

Gao²,

Shi

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

As one of the most crucial topics in the recommendation system field, point-of-interest (POI) recommendation aims to recommending potential interesting POIs to users. Recently, graph neural networks have been successfully used to model interaction and spatio-temporal information in POI recommendations, but the data sparsity of POI recommendations affects the training of GNNs. Although some existing GNN-based POI recommendation approaches try to use social relationships or user attributes to alleviate the data sparsity problem, such auxiliary information is not always available for privacy reasons. Self-supervised learning provides a new idea to alleviate the data sparsity problem, but most existing self-supervised recommendation methods are designed for bi-partite graphs or social graphs, and cannot be directly used in the spatio-temporal graph of POI recommendations. In this paper, we propose a new method named SSTGL to combine self-supervised learning and GNN-based POI recommendation for the first time. SSTGL is empowered with spatio-temporal-aware strategies in the data augmentation and pre-text task stages, respectively, so that it can provide high-quality supervision information by incorporating spatio-temporal prior knowledge. By combining self-supervised learning objective with recommendation objectives, SSTGL can improve the performance of GNN-based POI recommendations. Extensive experiments on three POI recommendation datasets demonstrate the effectiveness of SSTGL, which performed better than existing mainstream methods.

show abstract

Differential Privacy-Based Social Network Detection Over Spatio-Temporal Proximity for Secure POI Recommendation

Cited by 13 publications

References 31 publications

Locating Senior-Friendly Restaurants in a Community: A Bi-Objective Optimization Approach for Enhanced Equality and Convenience

Locating Senior-Friendly Restaurants in a Community: A Bi-Objective Optimization Approach for Enhanced Equality and Convenience

Long-Term Preference Mining With Temporal and Spatial Fusion for Point-of-Interest Recommendation

Self-Supervised Spatio-Temporal Graph Learning for Point-of-Interest Recommendation

Contact Info

Product

Resources

About