TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank

Abstract

Learning-to-Rank deals with maximizing the utility of a list of examples presented to the user, with items of higher relevance being prioritized. It has several practical applications such as large-scale search, recommender systems, document summarization and question answering. While there is widespread support for classification and regression based learning, support for learning-to-rank in deep learning has been limited. We propose TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework. It is highly configurable and provides easy-to-use APIs to support different scoring mechanisms, loss functions and evaluation metrics in the learning-to-rank setting. Our library is developed on top of TensorFlow and can thus fully leverage the advantages of this platform. For example, it is highly scalable, both in training and in inference, and can be used to learn ranking models over massive amounts of user activity data, which can include heterogeneous dense and sparse features. We empirically demonstrate the effectiveness of our library in learning ranking functions for large-scale search and recommendation applications in Gmail and Google Drive. We also show that ranking models built using our model scale well for distributed training, without significant impact on metrics. The proposed library is available to the open source community, with the hope that it facilitates further academic research and industrial applications in the field of learning-to-rank.

KDD 2019

References in corpus (8)

• Distributed Representations of Words and Phrases and their Compositionality
• TensorFlow: A system for large-scale machine learning
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Introducing LETOR 4.0 Datasets
• TensorFlow-Serving: Flexible, High-Performance ML Serving
• Neural Models for Information Retrieval
• TensorFlow Estimators: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks

Cited by in corpus (26)

• Information Retrieval: Recent Advances and Beyond
• UniGrasp: Learning a Unified Model to Grasp with Multifingered Robotic Hands
• Pretrained Transformers for Text Ranking: BERT and Beyond
• Learning Groupwise Multivariate Scoring Functions Using Deep Neural Networks
• MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching
• Listwise Learning to Rank by Exploring Unique Ratings
• Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset
• Self-Attentive Document Interaction Networks for Permutation Equivariant Ranking
• LibAUC: A Deep Learning Library for X-Risk Optimization
• Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers
• Domain Adaptation for Enterprise Email Search
• Towards Multi-Language Recipe Personalisation and Recommendation
• Learning to Rank Graph-based Application Objects on Heterogeneous Memories
• Interpretable Learning-to-Rank with Generalized Additive Models
• Argument Undermining: Counter-Argument Generation by Attacking Weak Premises
• Separate and Attend in Personal Email Search
• Rethinking Click Models in Light of Carousel Interfaces: Theory-Based Categorization and Design of Click Models
• SERank: Optimize Sequencewise Learning to Rank Using Squeeze-and-Excitation Network
• Reusable Self-Attention Recommender Systems in Fashion Industry Applications
• Federated Unbiased Learning to Rank
• Counterfactual Learning to Rank using Heterogeneous Treatment Effect Estimation
• GLOW : Global Weighted Self-Attention Network for Web Search
• Exposure-Based Reinforcement Learning to Rank
• Unbiased Pairwise Learning to Rank in Recommender Systems
• Automatic Compilation of Resources for Academic Writing and Evaluating with Informal Word Identification and Paraphrasing System
• "It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems