Transformer-Based Multi-task Learning for Queuing Time Aware Next POI Recommendation

Halder, Sajal; Lim, Kwan Hui; Chan, Jeffrey; Zhang, Xiuzhen

doi:10.1007/978-3-030-75765-6_41

Cited by 17 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work is an extension of our previous conference paper (Halder et al 2021). Here we extend POI description based personalised user interest impacts on queuing time prediction and next POI recommendation simultaneously.…”

Section: Introductionmentioning

confidence: 66%

“…None of these studies used multi-tasking in POI recommendations. Halder et al (Halder et al 2021) proposed a transformer-based multi-task learning model for the next top-k POI recommendation and predicted queue time. This model can not capture user interests appropriately and can not solve the new POI cold start problem.…”

Section: Transformer and Multi-task Learningmentioning

confidence: 99%

“…Similarly, user feature embedding is to learn an encoding that can capture user visiting behavior property. Most of existing studies (Huang et al 2019;Zhou et al 2019a;Halder et al 2021) used unique user identity as a user feature and could not appropriately capture user behavior. In this paper, we measure user similarity based on their previous visiting POI description similarity.…”

Section: Feature Embeddingmentioning

confidence: 99%

“…Transformer allows multi-tasking that relies entirely on the attention mechanism to compute its input and output dependencies. In our early work TLR-M (Halder et al 2021), we proposed multi-attention layer-based transformer network leveraging complex spatiotemporal dependencies whereas user personal interest based on temporal influence is ignored. To address this issue, we use POI description similarity based personalised interest to recommend POIs and predict queuing time simultaneously.…”

Section: Introductionmentioning

confidence: 99%

“…To address this issue, we use POI description similarity based personalised interest to recommend POIs and predict queuing time simultaneously. The main difference between our proposed model and earlier transformer based multitasking model TLR-M (Halder et al 2021) is that our model incorporates user interests from one POI to another POI based on POIs descriptions which can solve POI cold start problem whereas existing TLR-M (Halder et al 2021) does not consider user interest. To sum up, in this paper we aim to answer the following research questions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

POI recommendation with queuing time and user interest awareness

Halder

Lim

Chan

et al. 2022

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

Point-of-interest (POI) recommendation is a challenging problem due to different contextual information and a wide variety of human mobility patterns. Prior studies focus on recommendation that considers user travel spatiotemporal and sequential patterns behaviours. These studies do not pay attention to user personal interests, which is a significant factor for POI recommendation. Besides user interests, queuing time also plays a significant role in affecting user mobility behaviour, e.g., having to queue a long time to enter a POI might reduce visitor’s enjoyment. Recently, attention-based recurrent neural networks-based approaches show promising performance in the next POI recommendation task. However, they are limited to single head attention, which can have difficulty in finding the appropriate user mobility behaviours considering complex relationships among POI spatial distances, POI check-in time, user interests and POI queuing times. In this research work, we are the first to consider queuing time and user interest awareness factors for next POI recommendation. We demonstrate how it is non-trivial to recommend a next POI and simultaneously predict its queuing time. To solve this problem, we propose a multi-task, multi-head attention transformer model called TLR-M_UI. The model recommends the next POIs to the target users and predicts queuing time to access the POIs simultaneously by considering user mobility behaviours. The proposed model utilises POIs description-based user personal interest that can also solve the new categorical POI cold start problem. Extensive experiments on six real-world datasets show that the proposed models outperform the state-of-the-art baseline approaches in terms of precision, recall, and F1-score evaluation metrics. The model also predicts and minimizes the queuing time. For the reproducibility of the proposed model, we have publicly shared our implementation code at GitHub (https://github.com/sajalhalder/TLR-M_UI).

show abstract

Section: Introductionmentioning

confidence: 66%

Section: Transformer and Multi-task Learningmentioning

confidence: 99%

Section: Feature Embeddingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

POI recommendation with queuing time and user interest awareness

Halder

Lim

Chan

et al. 2022

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

show abstract

Strategic and Crowd-Aware Itinerary Recommendation

Liu

Wood

Lim

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Itinerary recommendation is a complex sequence prediction problem with numerous real-world applications. This task becomes even more challenging when considering the optimization of multiple user queuing times and crowd levels, as well as numerous involved parameters, such as attraction popularity, queuing time, walking time, and operating hours. Existing solutions typically focus on single-person perspectives and fail to address real-world issues resulting from natural crowd behavior, like the Selfish Routing problem. In this paper, we introduce the Strategic and Crowd-Aware Itinerary Recommendation (SCAIR) algorithm, which optimizes group utility in real-world settings. We model the route recommendation strategy as a Markov Decision Process and propose a State Encoding mechanism that enables real-time planning and allocation in linear time. We evaluate our algorithm against various competitive and realistic baselines using a theme park dataset, demonstrating that SCAIR outperforms these baselines in addressing the Selfish Routing problem across four theme parks.

show abstract

STaTRL: Spatial-temporal and text representation learning for POI recommendation

Wang

Fukumoto

et al. 2022

Appl Intell

View full text Add to dashboard Cite

Transformer-Based Multi-task Learning for Queuing Time Aware Next POI Recommendation

Cited by 17 publications

References 16 publications

POI recommendation with queuing time and user interest awareness

POI recommendation with queuing time and user interest awareness

Strategic and Crowd-Aware Itinerary Recommendation

STaTRL: Spatial-temporal and text representation learning for POI recommendation

Contact Info

Product

Resources

About