MedLDA: maximum margin supervised topic models

By Jun Zhu, Amr Ahmed, Eric P. Xing. 2012

238 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.

1. Zhe Gan
2. Mohit Bansal
3. Chunyuan Li
4. Noah A. Smith
5. Percy Liang
6. Luke S. Zettlemoyer
7. Jun Zhu
8. Eric Wallace

Citations in the corpus

• Improving Interpretability of Deep Neural Networks with Semantic Information (2017, methodology): “Here, we adopt the most popular topic model, i.e ., Latent Dirichlet Allocation (LDA) [4], which has been applied to image/video/text analysis tasks [13, 7, 6, 40].”
• The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification (2014, methodology): “01) matches that reported previously for this dataset when using a combined LDA and SVM approach [33].”
• DEMix Layers: Disentangling Domains for Modular Language Modeling (2021, methodology): “Incorporating Metadata Document metadata has been commonly used to improve the quality of topic models (Mimno and McCallum, 2012; Ramage et al., 2009; Zhu et al., 2012), and previous works have used metadata for adapting RNN-based language models (Jaech and Ostendorf, 2018) or learning better docume”
• Discriminative Deep Random Walk for Network Classification (2016, methodology): “This idea of combining task-specific and representation objectives has been widely explored in other regions such as MedLDA (Zhu et al., 2012) and Supervised Dictionary Learning (Mairal et al., 2009).”
• Deep Poisson Factor Modeling (2015, methodology): “We could not improve results by increasing the size of our model, however, we may be able to do so by following the approach of [33], where a single classification module (SVM) is shared by 20 one-layer topic models (LDAs).”
• Network Representation Learning: A Survey (2017, methodology): “Inspired by the discriminative representation learning [64], [65], DDRW [45] proposes to learn discriminative network representations through jointly optimizing the objective of DeepWalk [6] together with the following L2-loss Support Vector Classification objective”
• An overview of topic modeling and its current applications in bioinformatics (2016, methodology): “2009), and maximum entropy discrimination LDA (medLDA) (Zhu et al. 2012).”
• Dirichlet-Derived Multiple Topic Scene Classification Model for High Spatial Resolution Remote Sensing Imagery (2016, methodology): “, correlated LDA [35], hierarchical Dirichlet processes [36], supervised LDA [37], maximum entropy discriminative LDA [38], geometric LDA [39], and so on.”
• Max-Margin Deep Generative Models (2015, background): “We expect that the supervision information will bias the learned representations to be more powerful on predicting the labels at testing.”
• WarpLDA: a Cache Efficient O(1) Algorithm for Latent Dirichlet Allocation (2015, methodology): “We then develop WarpLDA, which achieves O(1) time complexity per-token and fits the randomly accessed memory perdocument in the L3 cache.”
• Supervised topic models for clinical interpretability (2016, background): “The most natural extension is supervised LDA (McAuliffe and Blei, 2007), though other attempts exist (Zhu et al., 2012; Lacoste-Julien et al., 2009).”
• Interactive and interpretable machine learning models for human machine collaboration (2015, methodology): “01) matches that reported previously for this dataset when using a combined LDA and SVM approach [136].”
• WarpLDA: a Simple and Efficient O(1) Algorithm for Latent Dirichlet Allocation (2015, background): “Advantages of WarpLDA include 1) Efficiency and scalability: WarpLDA has good locality and carefully designed partition method, and can be scaled to hundreds of machines; 2) Simplicity: WarpLDA does not have any complicated modules such as alias tables, hybrid data structures, or parameter servers,…”
• Max-Margin DeepWalk: Discriminative Learning of Network Representation (2016, methodology): “Inspired by max-margin learning on topic model [Zhu et al., 2012], we present max-margin DeepWalk (MMDW) to learn discriminative representations of vertices in social networks.”
• Spectral Methods for Supervised Topic Models (2014, background): “Some representative models are supervised LDA (sLDA) [8] that captures a real-valued regression response for each document, multiclass sLDA [21] that learns with discrete classification responses, discriminative LDA (DiscLDA) [14] that incorporates classification response via discriminative linear t”