# Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sampling

arXiv: https://arxiv.org/abs/2104.15046 · HTML: https://mlsanity.com/paper/2104.15046/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 30 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [Black Box Variational Inference](https://mlsanity.com/paper/1401.0118/) (2013)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [Seq2Slate: Re-ranking and Slate Optimization with RNNs](https://mlsanity.com/paper/1810.02019/) (2018)
- [Evaluation of Session-based Recommendation Algorithms](https://mlsanity.com/paper/1803.09587/) (2018)
- [Metadata Embeddings for User and Item Cold-start Recommendations](https://mlsanity.com/paper/1507.08439/) (2015)
- [Deep Bayesian Bandits: Exploring in Online Personalized Recommendations](https://mlsanity.com/paper/2008.00727/) (2020)
- [Variational Tempering](https://mlsanity.com/paper/1411.1810/) (2014)
- [TripClick: The Log Files of a Large Health Web Search Engine](https://mlsanity.com/paper/2103.07901/) (2021)
- [Improving Collaborative Metric Learning with Efficient Negative Sampling](https://mlsanity.com/paper/1909.10912/) (2019)
- [Scalable Recommendation with Poisson Factorization](https://mlsanity.com/paper/1311.1704/) (2013)
- [Deep neural network marketplace recommenders in online experiments](https://mlsanity.com/paper/1809.02130/) (2018)

## Built on by (most cited first, 5 of 5)

- [FINN.no Slates Dataset: A new Sequential Dataset Logging Interactions, allViewed Items and Click Responses/No-Click for Recommender Systems Research](https://mlsanity.com/paper/2111.03340/) (2021)
- [Impression-Aware Recommender Systems](https://mlsanity.com/paper/2308.07857/) (2023)
- [Counterfactual Inference under Thompson Sampling](https://mlsanity.com/paper/2504.08773/) (2025)
- [On the Reliability of Sampling Strategies in Offline Recommender Evaluation](https://mlsanity.com/paper/2508.05398/) (2025)
- [Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation](https://mlsanity.com/paper/2609.37800/) (2026)

## Abstract (arXiv)

We consider the problem of recommending relevant content to users of an internet platform in the form of lists of items, called slates. We introduce a variational Bayesian Recurrent Neural Net recommender system that acts on time series of interactions between the internet platform and the user, and which scales to real world industrial situations. The recommender system is tested both online on real users, and on an offline dataset collected from a Norwegian web-based marketplace, FINN.no, that is made public for research. This is one of the first publicly available datasets which includes all the slates that are presented to users as well as which items (if any) in the slates were clicked on. Such a data set allows us to move beyond the common assumption that implicitly assumes that users are considering all possible items at each interaction. Instead we build our likelihood using the items that are actually in the slate, and evaluate the strengths and weaknesses of both approaches theoretically and in experiments. We also introduce a hierarchical prior for the item parameters based on group memberships. Both item parameters and user preferences are learned probabilistically. Furthermore, we combine our model with bandit strategies to ensure learning, and introduce `in-slate Thompson Sampling' which makes use of the slates to maximise explorative opportunities. We show experimentally that explorative recommender strategies perform on par or above their greedy counterparts. Even without making use of exploration to learn more effectively, click rates increase simply because of improved diversity in the recommended slates.