Time-Sensitive Recommendation From Recurrent User Activities

By Nan Du, Yichen Wang, Niao He, Jimeng Sun, Le Song. 2015

137 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

DRN: A Deep Reinforcement Learning Framework for News Recommendation (2018, methodology): “Although we use survival models here to estimate the user activeness, other alternatives like Poisson point process [13] can also be applied and should serve similar function.”
Embedding Temporal Network via Neighborhood Formation (2018, background): “Particularly, recent studies on Hawkes process mainly focus on tackling the challenges of scalability by employing the memoryless property [15] or imposing the low-rank structure on the infectivity matrix [7, 14], etc.”
Neural Survival Recommender (2017, methodology): “In [9], the author proposed a more advanced Hawkes process coupled with low-rank penalty to solve similar problem.”
Latent Cross: Making Use of Context in Recurrent Recommender Systems (2018, methodology): “More general abstractions have been used to model preference evolution for recommendation such as point processes [15] and recurrent neural networks [43].”
Returning is Believing: Optimizing Long-term User Engagement in Recommender Systems (2017, background): “[10] combined a self-exciting point process with low rank models to capture the recurrent temporal paerns in user-item consumption.”
The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process (2017, methodology): “…Hawkes process has been widely used to model event streams, including for topic modeling and clustering of text document streams (He et al., 2015; Du et al., 2015a), constructing and inferring 4Appendix A.2 explains how our LSTM handles the start and end of the sequence. network structure (Yang…”
Recurrent Marked Temporal Point Processes: Embedding Event History to Vector (2016, background): “More recently, the self-excitation point process [20], has become an ongoing hot topic for modeling the latent dynamics of information diffusion [16, 9, 10, 8, 40, 14, 22], online-user engagement [13], news-feed streams [7], and context-aware recommendations [11].”
Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs (2017, methodology): “Hence we devised two baseline methods for evaluating time prediction performance — (i) Multi-dimensional Hawkes process (MHP): We model dyadic entity interactions as multi-dimensional Hawkes process similar to (Du et al., 2015).”