Curriculum Meta-Learning for Next POI Recommendation

Chen, Yudong; Wang, Xin; Fan, Miao; Huang, Jizhou; Yang, Shengwen; Zhu, Wenwu

doi:10.1145/3447548.3467132

Cited by 46 publications

(16 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Task #5: Next POI Recommendation. Given a user's sequence of historical POI visits, the task of next POI recommendation (NPR) [4,33] aims at recommending a list of POIs that the user is most likely to visit consequently. NPR is an essential feature in the information page of Baidu Maps, which can help users explore the neighborhood with minimal operations.…”

Section: Geo-related Tasksmentioning

confidence: 99%

“…The web mapping services provided by Baidu Maps, such as point of interest (POI) retrieval [12], POI auto-completion [7,13], POI recommendation [4], and POI information page [29], have shown improved performance by applying PTMs. However, a clear performance plateau over time was observed in our practice, i.e., the performance gain remains marginal w.r.t.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps

Huang,

Wang,

Sun

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Pre-trained models (PTMs) have become a fundamental backbone for downstream tasks in natural language processing and computer vision. Despite initial gains that were obtained by applying generic PTMs to geo-related tasks at Baidu Maps, a clear performance plateau over time was observed. One of the main reasons for this plateau is the lack of readily available geographic knowledge in generic PTMs. To address this problem, in this paper, we present POLARIS, which is a geographic pre-trained model designed and developed for improving the geo-related tasks at Baidu Maps. POLARIS is elaborately designed to learn a universal representation of geography-language by pre-training on large-scale data generated from a heterogeneous graph that contains abundant geographic knowledge. Extensive quantitative and qualitative experiments conducted on large-scale real-world datasets demonstrate the superiority and effectiveness of POLARIS. POLARIS has already been deployed in production at Baidu Maps since April 2021, which significantly benefits the performance of a wide range of downstream tasks. This demonstrates that POLARIS can serve as a fundamental backbone for geo-related tasks. CCS CONCEPTS• Information systems → Data mining.

show abstract

Section: Geo-related Tasksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps

Huang,

Wang,

Sun

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…After the multi-head attention matrix A j has been calculated for all addresses through the forward process, we derive the weighted address embedding H through multiplication and concatenation as in Eqn. (9).…”

Section: Address Representation Modulementioning

confidence: 99%

FastAddr

Hong

Yang

Wang

et al. 2022

Proceedings of the 30th International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

An address, a textual description of a physical location, plays an important role in location-based services such as on-demand delivery and e-commerce. However, abnormal addresses (i.e., an address without detailed information representing a spatial location) have led to significant costs. In real-world settings like e-commerce, abnormal address detection is not trivial because it needs to be completed in real-time to support massive online queries. In this study, we design FastAddr, a fast abnormal address detection framework, which detects abnormal addresses among millions of addresses in a short time. By investigating and modeling the hierarchical structure of address data, we first design a novel contrastive address augmentation approach to generate training data via learning the entity transition probability matrix. We further design a lightweight multi-head attention model for learning compact address representation by modeling the address characteristics. We conduct a comprehensive three-phase evaluation. (i) We evaluate FastAddr on a real-world dataset and it yields the average F1 of 85.7% in 0.058 milliseconds, which outperforms the state-of-the-art models by 47.4% with similar detection time. (ii) An offline A/B test shows that FastAddr outperforms the previous deployed model significantly. (iii) We also conduct an online A/B test to compare FastAddr with the deployed model, which shows an improvement of F1 by more than 20%. Moreover, a real-world case study demonstrates both the efficiency and effectiveness of FastAddr.

show abstract

“…Third, some MAML-based methods [7], [14], [15], [19] use complicated neural networks in their systems. These models require users with dozens or hundreds of records to optimize the global and local parameters.…”

Section: Introductionmentioning

confidence: 99%

HyperRS: Hypernetwork-Based Recommender System for the User Cold-Start Problem

Nakamura

Ichise

2023

IEEE Access

View full text Add to dashboard Cite

Meta-learning has been proven to be effective for the cold-start problem of recommender systems. Many meta-learning recommender systems that are designed for the user cold-start problem are gradient-based. They use a global parameter learned from existing users to initialize the recommender system parameter for new users that provides a personalized recommendation with limited user-item interactions. Many systems require users' demographic information to learn the global parameter. This requirement raises privacy concerns, and demographic information is not always available. In addition, some of the gradient-based systems need dozens or even hundreds of user-item interactions from existing users to learn the global parameter. This requirement is difficult to satisfy in specific scenarios in which active users and their item interactions are rare. Moreover, gradient-based meta-learning systems rarely capture user preferences over different item attributes, as updating the corresponding weights requires many optimization steps. We proposed HyperRS, a Hypernetwork-based Recommender System, for the user cold-start problem. Our system does not rely on demographic information to provide personalized recommendations. In our system, a hypernetwork generates all weights in the underlying recommender system. The hypernetwork enables the weights to adapt quickly to capture user interest in both item attributes and the contents of the item attributes. The experimental results show that our method outperforms several state-of-the-art meta-learning recommender systems for the user cold-start problem.

show abstract

Curriculum Meta-Learning for Next POI Recommendation

Cited by 46 publications

References 40 publications

ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps

ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps

FastAddr

HyperRS: Hypernetwork-Based Recommender System for the User Cold-Start Problem

Contact Info

Product

Resources

About