Scalable inference of topic evolution via models for latent geometric structures
By Mikhail Yurochkin, Zhiwei Fan, Aritra Guha, Paraschos Koutris, XuanLong Nguyen. 2018
12 citations recorded by the source corpus.
We develop new models and algorithms for learning the temporal dynamics of the topic polytopes and related geometric objects that arise in topic model based inference. Our model is nonparametric Bayesian and the corresponding inference algorithm is able to discover new topics as the time progresses. By exploiting the connection between the modeling of topic polytope evolution, Beta-Bernoulli process and the Hungarian matching algorithm, our method is shown to be several orders of magnitude faster than existing topic modeling approaches, as demonstrated by experiments working with several million documents in under two dozens of minutes.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Hongyi Wang
- Mikhail Yurochkin
- Dimitris Papailiopoulos
- Yasaman Khazaeni
- Yuekai Sun
- Soumya Ghosh
- Trong Nghia Hoang
- Mayank Agarwal
In Computer Vision and Pattern Recognition
- Soumya Ghosh
- Dimitris Papailiopoulos
- Hongyi Wang
- Yasaman Khazaeni
- Kristjan H. Greenewald
- Yuekai Sun
- Mikhail Yurochkin
Citations in the corpus
- Federated Learning with Matched Averaging (2020, methodology): “The immediate consequence of our result is the extension of PFNM (Yurochkin et al., 2019b) to CNNs. Empirically, see Figure 1, we found that this extension performs well on MNIST with a simpler CNN architecture such as LeNet (LeCun et al., 1998) (4 layers) and significantly outperforms…”
- Bayesian Nonparametric Federated Learning of Neural Networks (2019, methodology): “Our work is related to a recent application of these ideas to distributed topic modeling (Yurochkin et al., 2018), where the authors use the BBP for modeling topics learned from multiple collections of document, and provide an inference scheme based on the Hungarian algorithm (Kuhn, 1955).”
- Statistical Model Aggregation via Parameter Matching (2019, unknown): “In the context of our meta model this problem has been studied when distributions in (1) and (4) are Gaussian [32] or von Mises-Fisher [33], which are both special cases of our meta model.”