Ranking & Recommendations

Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation

September 27, 2021

Abstract

Much of the recent progress in sequential and session-based recommendation has been driven by improvements in model architecture and pretraining techniques originating in the field of Natural Language Processing. Transformer architectures in particular have facilitated building higher-capacity models and provided data augmentation and training techniques which demonstrably improve the effectiveness of sequential recommendation. But with a thousandfold more research going on in NLP, the application of transformers for recommendation understandably lags behind. To remedy this we introduce Transformers4Rec, an open-source library built upon HuggingFace's Transformers library with a similar goal of opening up the advances of NLP based Transformers to the recommender system community and making these advancements immediately accessible for the tasks of sequential and session-based recommendation. Like its core dependency, Transformers4Rec is designed to be extensible by researchers, simple for practitioners, and fast and robust in industrial deployments.
In order to demonstrate the usefulness of the library and the applicability of Transformer architectures in next-click prediction for user sessions, where sequence lengths are much shorter than those commonly found in NLP, we have leveraged Transformers4Rec to win two recent session-based recommendation competitions. In addition, we present in this paper the first comprehensive empirical analysis comparing many Transformer architectures and training approaches for the task of session-based recommendation. We demonstrate that the best Transformer architectures have superior performance across two e-commerce datasets while performing similarly to the baselines on two news datasets. We further evaluate in isolation the effectiveness of the different training techniques used in causal language modeling, masked language modeling, permutation language modeling and replacement token detection for a single Transformer architecture, XLNet. We establish that training XLNet with replacement token detection performs well across all datasets. Finally, we explore techniques to include side information such as item and user context features in order to establish best practices and show that the inclusion of side information uniformly improves recommendation performance.

Download the Paper

AUTHORS

Written by

Gabriel de Souza Pereira Moreira

Sara Rabhi

Jeong Min Lee

Ronay Ak

Even Oldridge

Publisher

RecSys 2021

Related Publications

November 30, 2020

Theory

Ranking & Recommendations

On ranking via sorting by estimated expected utility

Nicolas Usunier, Clément Calauzènes

November 30, 2020

February 01, 2021

Ranking & Recommendations

Anytime Inference with Distilled Hierarchical Neural Ensembles

Adria Ruiz, Jakob Verbeek

February 01, 2021

November 01, 2018

Ranking & Recommendations

Horizon: Facebook's Open Source Applied Reinforcement Learning Platform | Facebook AI Research

Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Yuchen He, Zachary Kaden, Vivek Narayanan, Xiaohui Ye

November 01, 2018

December 03, 2018

Ranking & Recommendations

NLP

Training with Low-precision Embedding Tables | Facebook AI Research

Jian Zhang, Jiyan Yang, Hector Yuen

December 03, 2018

May 03, 2019

Ranking & Recommendations

Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search | Facebook AI Research

Jinfeng Rao, Wei Yang, Yuhao Zhang, Ferhan Ture, Jimmy Lin

May 03, 2019

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.