Efficient Inference for Dynamic Topic Modeling with Large Vocabularies


Dynamic topic modeling is a well established tool for capturing the temporal dynamics of the topics of a corpus. Currently, dynamic topic models can only consider a small set of frequent words because of their computational complexity and insufficient data for less frequent words. In this work, we de- velop a scalable dynamic topic model by utilizing the correlation among the words in the vocabulary. By correlating previously independent temporal processes for words, our new model allows us to reliably estimate the topic representations contain- ing less frequent words. We develop an amortised variational inference method with self-normalised importance sampling approximation to the word distribution that dramatically reduces the compu- tational complexity and the number of variational parameters in order to handle large vocabularies. With extensive experiments on text datasets, we show that our method significantly outperforms the previous works by modeling word correlations, and it is able to handle real world data with a large vocabulary (80K words) which could not be pro- cessed by previous continuous dynamic topic mod- els. With qualitative analyses, we show that our method can perform inference on infrequent but representative keywords much more reliably than previous methods.


May 2024 | The Web Conference

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks

Marco De Nadai, Francesco Fabbri, Paul Gigioli, Alice Wang, Ang Li, Fabrizio Silvestri, Laura Kim, Shawn Lin, Vladan Radosavljevic, Sandeep Ghael, David Nyhan, Hugues Bouchard, Mounia Lalmas-Roelleke, Andreas Damianou

May 2024 | The Web Conference (GFM workshop)

Towards Graph Foundation Models for Personalization

Andreas Damianou, Francesco Fabbri, Paul Gigioli, Marco De Nadai, Alice Wang, Enrico Palumbo, Mounia Lalmas

April 2024 | ICLR

In-context Exploration-Exploitation for Reinforcement Learning

Zhenwen Dai, Federico Tomasi, Sina Ghiassian