Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes

By Yee Whye Teh, Michael I. Jordan, Matthew J. Beal, David M. Blei. 2004

583 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

RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “This compound HDP-DBM model learns novel concepts from very few training examples by learning: (i) low-level generic features, (ii) high-level features that capture correlations among low-level features and, (iii) a category hierarchy for sharing priors over the high-level features that are typical ”
On Finding the Natural Number of Topics with Latent Dirichlet Allocation: Some Observations (2010, methodology): “There have also been approaches like Hierarchical Dirichlet Process (HDP) [ 11 ] which try to find the right number of topics by assuming that the data has a hierarchical structure to it. Here, both HDP as well as LDA models for the same dataset are built and compared to find the right number of top”
Topic and Role Discovery in Social Networks (2005, background): “Hierarchical Dirichlet Processes [Teh et al., 2004] can determine an appropriate number of topics for a corpus.”
Topic Compositional Neural Language Model (2017, background): “, 2003), significant extensions have been proposed, including capturing topic correlations (Blei and Lafferty, 2007), modeling temporal dependencies (Blei and Lafferty, 2006), discovering an unbounded number of topics (Teh et al., 2005), learning deep architectures (Henao et al.”
Topic Modeling Using Latent Dirichlet allocation (2021, methodology): “[131] 2005 Chinese Restaurant Process (CRP) Gibbs sampling Collapsed Gibbs sampling Each group of data comprises of number of components”
Analysis of Representations for Domain Adaptation (2006, background): “While many authors have analyzed adaptation from multiple sets of labeled training data [3, 5, 7, 13], our theory applies to the setting in which the target domain has no labeled training data, but plentiful unlabeled data exists for both target and source domains.”
Backward Feature Correction: How Deep Learning Performs Deep Learning (2020, background): “In machine learning, hierarchical learning is also the key to success for many models, such as hierarchical linear models [55], Bayesian networks/probabilistic directed acyclic graphical models [20], hierarchical Dirichlet allocation [52], hierarchical clustering [47], deep belief networks [39].”
Convex Discriminative Multitask Clustering (2013, background): “1) In respect of “what to learn”, in [37], Teh et al.”
Variational Russian Roulette for Deep Bayesian Nonparametrics (2019, methodology): “Within machine learning, Bayesian nonparametric methods have been applied within models as diverse as clustering (Antoniak, 1974; Görür & Rasmussen, 2010; Teh et al., 2005), topic modeling (Teh et al., 2006), and infinite deep neural networks (Adams et al., 2010).”
Topic modelling for qualitative studies (2017, methodology): “Finally, a lot of work has been done on non-parametric LDA variants based on Dirichlet processes that we will not go into in this paper; for the most important non-parametric approaches to LDA see previous studies [25–29] and references therein.”
Statistical Model Aggregation via Parameter Matching (2019, unknown): “Hierarchical Bayesian models [3, 12, 29] are widely used for performing such analyses, as they are able to both naturally model heterogeneity in data and share statistical strength across heterogeneous groups.”
Modeling Islamist Extremist Communications on Social Media using Contextual Dimensions (2019, methodology): “s of our approach to disambiguate content, we create the negative class dataset from a dataset of Muslim religious users. We employ Hierarchical Dirichlet Processing (HDP) (non-parametric) clustering [56] on the tweets from users to hierarchically organize users probabilistically based on their cont”