Seq2Slate: Re-ranking and Slate Optimization with RNNs

Abstract

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.

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Universal Transformers
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• Neural Combinatorial Optimization with Reinforcement Learning
• Gradient Estimation Using Stochastic Computation Graphs
• Learning Latent Permutations with Gumbel-Sinkhorn Networks
• Neural Models for Information Retrieval
• Ranking via Sinkhorn Propagation
• Deep Choice Model Using Pointer Networks for Airline Itinerary Prediction
• Learning Permutations with Sinkhorn Policy Gradient
• An Attention-Based Deep Net for Learning to Rank

Cited by in corpus (19)

• RecSim: A Configurable Simulation Platform for Recommender Systems
• Controllable Multi-Objective Re-ranking with Policy Hypernetworks
• Context-Aware Learning to Rank with Self-Attention
• Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology
• SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
• Personalized Re-ranking for Recommendation
• Self-Attentive Document Interaction Networks for Permutation Equivariant Ranking
• Set-to-Sequence Methods in Machine Learning: a Review
• AliExpress Learning-To-Rank: Maximizing Online Model Performance without Going Online
• Explainable Product Search with a Dynamic Relation Embedding Model
• GRN: Generative Rerank Network for Context-wise Recommendation
• Context-aware Reranking with Utility Maximization for Recommendation
• Reinforcement Re-ranking with 2D Grid-based Recommendation Panels
• An Attention Module for Convolutional Neural Networks
• SERank: Optimize Sequencewise Learning to Rank Using Squeeze-and-Excitation Network
• Optimize What You Evaluate With: A Simple Yet Effective Framework For Direct Optimization Of IR Metrics
• UAV Trajectory Planning in Wireless Sensor Networks for Energy Consumption Minimization by Deep Reinforcement Learning
• Conditional Sequential Slate Optimization
• Combining Reward and Rank Signals for Slate Recommendation