Time weight collaborative filtering

By Yi Ding, Xue Li. 2005

521 citations recorded by the source corpus.

Subfields: Information Systems, Marketing, Sociology and Political Science

How researchers see this paper

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

In Information Systems

In Marketing

In Sociology and Political Science

Citations in the corpus

Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering (2016, background): “[7] propose a time weighting scheme to assign decaying weights to previously-rated items according to the time difference.”
From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews (2013, background): “As discussed in [20], few previous works had dealt with temporal dynamics, other than a few notable exceptions [2, 10, 35].”
Temporal recommendation on graphs via long- and short-term preference fusion (2010, methodology): “[2] and Andreas [23] both proposed a timeweighted item-based collaborative filtering method (TItemKNN) by reducing the influence of old data when predicting users’ further behavior.”
Collaborative filtering with temporal dynamics (2010, background): “Nonetheless, with very few exceptions (e.g., Ding and Li, and Sugiyama et al. 4, 16 ), the recommenders’ literature does not address temporal changes in user behavior.”
Streaming Recommender Systems (2016, background): “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].”
Time-aware point-of-interest recommendation (2013, methodology): “In other domains time factor is considered for recommendation in several studies, including using item-based CF method [7], matrix factorization method [11] and random walk based method [19].”
Translation-based Recommendation (2017, background): “, [3]) uses time weighting schemes that assign decaying weights to previouslyrated items when computing similarities.”
Recommender Systems (2012, background): “Ding and Li [292] weighed different items by putting smaller weights on older ones.”
Recommender Systems (2016, unknown): “A decay function, which is commonly used [185], is the exponential function:”
Online Machine Learning in Big Data Streams (2018, unknown): “Asanearly time-aware recommender system example, the item-based nearest neighbor [202] can be extended with time-decay [72].”
Temporal collaborative filtering with adaptive neighbourhoods (2009, background): “Temporality has also been explored from the point of view of changing user tastes [12]; in this case, ratings are scaled according to when they were input.”
Sequential User-based Recurrent Neural Network Recommendations (2017, methodology): “In [7], a fully personalized time-discounted version has been proposed by extending 𝑘 -NN with an exponential decaying component that penalizes items consumed a long time ago.”
Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols (2013, methodology): “Ding and Li (2005) obtained recommendation improvements by means of applying an exponential decay rate on old ratings in order to give more importance to recent ratings, arguing the latter should better reflect the users’ current tastes.”
Predicting the popularity of web 2.0 items based on user comments (2014, methodology): “To account for such latent signals in user comments, we first model user comments as a time-aware bipartite graph, and then predict future popularity based on this graph using a regularization framework [39], which enables the incorporation of multiple factors in a principled manner.”
A Distributed, Architecture-Centric Approach to Computing Accurate Recommendations from Very Large and Sparse Datasets (2011, background): “back form a more accurate representation of users’ changing preferences [24, 45, 46].”
Learning under Concept Drift: an Overview (2010, background): “in fo rm at io n pr ofi lin g re co m m en de r sy st em s m ov ie re co m m en da ti on s [8 4, 8, 39 ]”
SMF: Drift-Aware Matrix Factorization with Seasonal Patterns (2019, background): “Dynamic Matrix Factorization Timeweighting schemes weight past data by their recency [7, 8].”
Collaborative filtering with temporal dynamics (2009, background): “Notable discussions of temporal effects include Ding and Li [6], who suggested a time weighting scheme for a similaritybased collaborative filtering approach.”