Modeling Sequential Online Interactive Behaviors with Temporal Point Process

Cai, Renqin; Bai, Xueying; Wang, Zhenrui; Shi, Yuling; Sondhi, Parikshit; Wang, Honggang

doi:10.1145/3269206.3271782

Cited by 18 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Long-and Short-term Hawkes Process (LSHP). Cai et al [4] proposed a Long-and Short-term Hawkes Process that uses a unidimension Hawkes process to model transition patterns across sessions and a multi-dimension Hawkes process to model transition patterns within a session. Sequential Models.…”

Section: • First Order Markov Model (Markov) This Methods Makes Thementioning

confidence: 99%

“…Their model is designed to have better expressivity for complex temporal patterns and achieves better performance compared to the vanilla Hawkes process. The Long-and Short-Term Hawkes Process model [4] demonstrates a combination of Hawkes Process model for different segments of user history can improve the performance in predicting the type and time of the next action in sequential online interactive behavior modeling. However, most of these Hawkes process based algorithms model each typed event as a separate stochastic process and therefore cannot scale as the space of event type grows.…”

Section: Temporal Recommendationmentioning

confidence: 99%

“…The two datasets include user behaviors from two different application scenarios. The XING dataset is extracted from the Recsys Challenge 2016 dataset [29], which contains a set of user actions on job postings from a professional social network site 4 . Each action is associated with the user ID, item ID, action timestamp and interaction type (click, bookmark, delete, etc.).…”

Section: Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Déjà vu: A Contextualized Temporal Attention Mechanism for Sequential Recommendation

Cai

Wang

2020

Proceedings of the Web Conference 2020

Self Cite

View full text Add to dashboard Cite

Predicting users' preferences based on their sequential behaviors in history is challenging and crucial for modern recommender systems. Most existing sequential recommendation algorithms focus on transitional structure among the sequential actions, but largely ignore the temporal and context information, when modeling the influence of a historical event to current prediction.In this paper, we argue that the influence from the past events on a user's current action should vary over the course of time and under different context. Thus, we propose a Contextualized Temporal Attention Mechanism that learns to weigh historical actions' influence on not only what action it is, but also when and how the action took place. More specifically, to dynamically calibrate the relative input dependence from the self-attention mechanism, we deploy multiple parameterized kernel functions to learn various temporal dynamics, and then use the context information to determine which of these reweighing kernels to follow for each input. In empirical evaluations on two large public recommendation datasets, our model consistently outperformed an extensive set of state-of-the-art sequential recommendation methods.

show abstract

Section: • First Order Markov Model (Markov) This Methods Makes Thementioning

confidence: 99%

Section: Temporal Recommendationmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Déjà vu: A Contextualized Temporal Attention Mechanism for Sequential Recommendation

Cai

Wang

2020

Proceedings of the Web Conference 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…TPP model and its variants span a wide range of applications as event data is prevalent and becoming increasingly available such as online advertisement [29], [30], detection [31], pattern mining [32], information diffusion [33], prediction and recommendation [34]- [37]. For example, Xu et al [35] develop a framework for modeling the transition events of patient flow via point process, which can be used to predict patients' destination care units and duration days.…”

Section: B Temporal Point Processmentioning

confidence: 99%

“…Dutta et al [31] propose a fake retweeters detector named HawkesEye, which combines Hawkes process and topic model to fully utilize textual content data and time information for better detection performance. Cai et al [37] present a long-and short-term Hawkes process (LSHP) model, which combines two Hawkes processes to capture "mutual-influence" of different behaviors as well as "self-influence" of behaviors of the same type. Yang et al [36] design a novel Recurrent Spatio-Temporal Point Process (RSTPP) to learn the latent dependencies of event times over behavior sequences.…”

Section: B Temporal Point Processmentioning

confidence: 99%

Sequential Recommendation Based on Multivariate Hawkes Process Embedding With Attention

Wang

Zhang

Xiang

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Recommender systems are important approaches for dealing with the information overload problem in big data era, and various kinds of auxiliary information, including time and sequential information, can help to improve the performance of retrieval and recommendation tasks. However, it is still a challenging problem how to fully exploit such information to achieve high-quality recommendation results and improve users' experience. In this work, we present a novel sequential recommendation model named Multivariate Hawkes Process Embedding with attention (MHPE-a), which combines a temporal point process with attention mechanism to predict the items that the target user may interact with according to her/his historical records. Specifically, the proposed approach MHPE-a can model users' sequential patterns in their temporal interaction sequences accurately with a multivariate Hawkes process. Then, we perform accurate sequential recommendation to satisfy target users' realtime requirement based on their preferences obtained with MHPE-a from their historical records. Especially, an attention mechanism is used to leverage users' long/short-term preferences adaptively to achieve accurate sequential recommendation. Extensive experiments are conducted on two real-world datasets (lastfm and gowalla), and the results show that MHPE-a achieves better performance than state-of-the-art baselines.

show abstract

Modeling Periodic Pattern with Self-Attention Network for Sequential Recommendation

Liu²,

Sheng

et al. 2020

Database Systems for Advanced Applications

View full text Add to dashboard Cite

Modeling Sequential Online Interactive Behaviors with Temporal Point Process

Cited by 18 publications

References 28 publications

Déjà vu: A Contextualized Temporal Attention Mechanism for Sequential Recommendation

Déjà vu: A Contextualized Temporal Attention Mechanism for Sequential Recommendation

Sequential Recommendation Based on Multivariate Hawkes Process Embedding With Attention

Modeling Periodic Pattern with Self-Attention Network for Sequential Recommendation

Contact Info

Product

Resources

About