Modeling Spatiotemporal Periodicity and Collaborative Signal for Local-Life Service Recommendation
Abstract: Online local-life service platforms provide services like nearby daily essentials and food delivery for hundreds of millions of users. Different from other types of recommender systems, local-life service recommendation has the following characteristics: (1) spatiotemporal periodicity, which means a user's preferences for items vary from different locations at different times. (2) spatiotemporal collaborative signal, which indicates similar users have similar preferences at specific locations and times. However, most existing methods either focus on merely the spatiotemporal contexts in sequences, or model the user-item interactions without spatiotemporal contexts in graphs. To address this issue, we design a new method named SPCS in this paper. Specifically, we propose a novel spatiotemporal graph transformer (SGT) layer, which explicitly encodes relative spatiotemporal contexts, and aggregates the information from multi-hop neighbors to unify spatiotemporal periodicity and collaborative signal. With extensive experiments on both public and industrial datasets, this paper validates the state-of-the-art performance of SPCS.
- CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks. arXiv preprint arXiv:2307.02813 (2023).
- Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation. arXiv preprint arXiv:2208.00593 (2022).
- ST-PIL: Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation. In CIKM. 2960–2964.
- Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer. In CIKM. 433–442.
- STGCN: A Spatial-Temporal Aware Graph Learning Method for POI Recommendation. In ICDM. 1052–1057.
- Lightgcn: Simplifying and Powering Graph Convolution Network for Recommendation. In SIGIR. 639–648.
- Time Interval Aware Self-Attention for Sequential Recommendation. In WSDM. 322–330.
- Geography-aware sequential location recommendation. In KDD. 2009–2019.
- Predicting the next location: A recurrent model with spatial and temporal contexts. In AAAI.
- Exploiting geographical neighborhood characteristics for location recommendation. In CIKM. 739–748.
- Lynn H Loomis. 2013. Introduction to abstract harmonic analysis.
- Stan: Spatio-temporal attention network for next location recommendation. In WWW. 2177–2185.
- Point-of-interest recommendation: Exploiting self-attentive autoencoders with neighbor-aware influence. In CIKM. 697–706.
- Larry R Medsker and LC Jain. 2001. Recurrent neural networks. Design and Applications 5 (2001), 64–67.
- Pytorch: An imperative style, high-performance deep learning library. NIPS 32 (2019).
- BPR: Bayesian Personalized Ranking from Implicit Feedback. In UAI. 452–461.
- C Carl Robusto. 1957. The cosine-haversine formula. The American Mathematical Monthly 64, 1 (1957), 38–40.
- Temporal Graph Networks for Deep Learning on Dynamic Graphs. ICML’Workshop (2020).
- Where to go next: Modeling long-and short-term user preferences for point-of-interest recommendation. In AAAI, Vol. 34. 214–221.
- Temporal Contrastive Pre-Training for Sequential Recommendation. In CIKM. 1925–1934.
- Attention is all you need. NIPS 30 (2017).
- Modeling item-specific temporal dynamics of repeat consumption for recommender systems. In WWW. 1977–1987.
- Neural Graph Collaborative Filtering. SIGIR (2019), 165–174. arXiv:1905.08108
- Session-Based Recommendation with Graph Neural Networks. AAAI 33 (2019), 346–353. arXiv:1811.00855
- Inductive Representation Learning on Temporal Graphs. In ICLR.
- GETNext: trajectory flow map enhanced transformer for next POI recommendation. In SIGIR. 1144–1153.
- Deep Interest Evolution Network for Click-Through Rate Prediction. AAAI 33 (2019), 5941–5948.
- Deep interest network for click-through rate prediction. In KDD. 1059–1068.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.