Seq2Slate: Re-ranking and Slate Optimization with RNNs

By Irwan Bello, Sayali Kulkarni, Sagar Jain, Craig Boutilier, Ed H. Chi, Elad Eban, Xiyang Luo, Alan Mackey, Ofer Meshi. 2018

114 citations recorded by the source corpus.

Ranking is a central task in machine learning and information retrieval. In this task, it is especially important to present the user with a slate of items that is appealing as a whole. This in turn requires taking into account interactions between items, since intuitively, placing an item on the slate affects the decision of which other items should be placed alongside it. In this work, we propose a sequence-to-sequence model for ranking called seq2slate. At each step, the model predicts the next `best' item to place on the slate given the items already selected. The sequential nature of the model allows complex dependencies between the items to be captured directly in a flexible and scalable way. We show how to learn the model end-to-end from weak supervision in the form of easily obtained click-through data. We further demonstrate the usefulness of our approach in experiments on standard ranking benchmarks as well as in a real-world recommendation system.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research, Natural Language Processing, Reinforcement Learning

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

1. Quoc V. Le
2. Irwan Bello
3. Jianfeng Gao
4. Barret Zoph
5. Mohit Bansal
6. Kyunghyun Cho
7. Jonathon Shlens
8. Yoshua Bengio

In Information Systems

1. Yongfeng Zhang
2. Qingyao Ai
3. Zhe Zhao
4. W. Bruce Croft
5. Ed H. Chi
6. Lichan Hong
7. Yi Wu
8. Xu Chen

In Management Science and Operations Research

1. Ed H. Chi
2. Zhe Zhao
3. Lichan Hong
4. W. Bruce Croft
5. Craig Boutilier
6. Sanmit Narvekar
7. Yongfeng Zhang
8. Jonathon Shlens

In Natural Language Processing

1. Barret Zoph
2. W. Bruce Croft
3. Qingyao Ai
4. Quoc V. Le
5. Jianfeng Gao
6. Yongfeng Zhang
7. Graham Neubig
8. Kyunghyun Cho

In Reinforcement Learning

1. Quoc V. Le
2. Craig Boutilier
3. Sanmit Narvekar
4. Yongfeng Zhang
5. Jonathon Shlens
6. Vihan Jain
7. Eugene Ie
8. Ed H. Chi

Citations in the corpus

• Attention Augmented Convolutional Networks (2019, background): “Attention has enjoyed widespread adoption as a computational module for modeling sequences because of its ability to capture long distance interactions [2, 44, 4, 3].”
• Explainable Product Search with a Dynamic Relation Embedding Model (2019, background): “There are also many studies on applying deep learning technology on other complicated retrieval problems such as user modeling [14, 36] and context-aware relevance modeling [2, 8].”
• RecSim: A Configurable Simulation Platform for Recommender Systems (2019, methodology): “Slate recommendation has been explored in non-sequential settings, capturing point-wise user choice models using non-parametric means [Ai et al., 2018, Bello et al., 2018, Jiang et al., 2019].”
• Fairness in Recommendation Ranking through Pairwise Comparisons (2019, background): “This setup is pervasive in practice [34, 38, 24, 16, 36], but significant research goes into bridging the gap between pointwise predictions and ranking construction [1, 6].”