Collaborative filtering with temporal dynamics

By Yehuda Koren. 2010

416 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Marketing

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

In Marketing

Citations in the corpus

From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews (2013, background): “In other words, each user evolves on their own ‘personal clock’; this differs from other models of temporal dynamics, which model the evolution of user and product parameters on a single timescale [20, 40, 41].”
How algorithmic confounding in recommendation systems increases homogeneity and decreases utility (2017, background): “In considering the impact of recommendation systems, some investigations model temporal dynamics [34] or frame the system in an explore/exploit paradigm [37, 63].”
Collaborative Filtering beyond the User-Item Matrix (2014, background): “Note that reviews and comments, as discussed in previous subsection, together with other types of users’ feedback to items, can also be categorized as interaction-associated information as long as they provide additional information about the U-I interaction.”
TensorCast: forecasting and mining with coupled tensors (2018, background): “The Netflix challenge sprung the creation of several latent factor models with differing structure and/or regularization terms for this task [19,25], but there were also several approaches which showed that using the age of the link could lead to improved predictions [20].”
Time Interval Aware Self-Attention for Sequential Recommendation (2020, background): “Temporal recommendation [17, 29, 31, 35] focuses on modeling absolute timestamps to capture the temporal dynamics of users and items.”
Streaming Recommender Systems (2016, methodology): “In recent years, there is a large literature exploiting temporal information [8, 13, 25, 26] and it is evident that explicitly modeling temporal dynamics greatly improves the recommendation performance [13, 24].”
Recommender system application developments: A survey (2015, background): “Concept drift techniques [175] should be introduced into recommender systems to model users’ preference drift and improve the recommendation performance in a fast changing environment [176].”
Transfer Learning for Behavior Ranking (2017, neutral): “For recommendation with ratings and auxiliary data, many works have been published, including ratings and social networks [Tang et al. 2013], temporal and geometrical information [Koren 2010; Tan et al. 2014], user proﬁles and item descriptions [Zhen et al. 2009], and so on.”
Deep Learning Based Recommender System (2017, methodology): “AutoSVD++ [197] makes use of a contractive autoencoder [123] to learn item feature representations, then integrates them into the classic recommendation model, SVD++ [79].”
Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding (2018, background): “The index t for S ut denotes the order in which an action occurs in the sequence S u , not the absolute timestamp as in temporal recommendation like [14, 31, 34].”
Sequential User-based Recurrent Neural Network Recommendations (2017, methodology): “For example, baseline predictors can be added to the original framework to account for temporal dynamics [27].”
Personalized Recommendation System Based on Collaborative Filtering for IoT Scenarios (2020, background): “[42] added time information to user’s feature vector.”
Session-Based Social Recommendation via Dynamic Graph Attention Networks (2019, methodology): “Modeling user interests that change over time has already received some attention [5, 19, 39].”
Sequence-Aware Recommender Systems (2018, background): “Furthermore, a number of proposals on time-aware recommenders mainly rely on the matrix completion problem setting when modeling temporal dynamics [68].”