# Efficient Attribute Injection for Pretrained Language Models

arXiv: https://arxiv.org/abs/2109.07953 · HTML: https://mlsanity.com/paper/2109.07953/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Controlling Linguistic Style Aspects in Neural Language Generation](https://mlsanity.com/paper/1707.02633/) (2017)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [Controlling Output Length in Neural Encoder-Decoders](https://mlsanity.com/paper/1609.09552/) (2016)
- [Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters](https://mlsanity.com/paper/2102.08597/) (2021)
- [Generating Personalized Recipes from Historical User Preferences](https://mlsanity.com/paper/1909.00105/) (2019)
- [Robust Transfer Learning with Pretrained Language Models through Adapters](https://mlsanity.com/paper/2108.02340/) (2021)
- [Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks](https://mlsanity.com/paper/1906.04393/) (2019)
- [Improving Review Representations with User Attention and Product Attention for Sentiment Classification](https://mlsanity.com/paper/1801.07861/) (2018)
- [Rethinking Attribute Representation and Injection for Sentiment Classification](https://mlsanity.com/paper/1908.09590/) (2019)
- [Automatic Academic Paper Rating Based on Modularized Hierarchical Convolutional Neural Network](https://mlsanity.com/paper/1805.03977/) (2018)
- [Categorical Metadata Representation for Customized Text Classification](https://mlsanity.com/paper/1902.05196/) (2019)
- [Cold-Start Aware User and Product Attention for Sentiment Classification](https://mlsanity.com/paper/1806.05507/) (2018)

## Abstract (arXiv)

Metadata attributes (e.g., user and product IDs from reviews) can be incorporated as additional inputs to neural-based NLP models, by modifying the architecture of the models, in order to improve their performance. Recent models however rely on pretrained language models (PLMs), where previously used techniques for attribute injection are either nontrivial or ineffective. In this paper, we propose a lightweight and memory-efficient method to inject attributes to PLMs. We extend adapters, i.e. tiny plug-in feed-forward modules, to include attributes both independently of or jointly with the text. To limit the increase of parameters especially when the attribute vocabulary is large, we use low-rank approximations and hypercomplex multiplications, significantly decreasing the total parameters. We also introduce training mechanisms to handle domains in which attributes can be multi-labeled or sparse. Extensive experiments and analyses on eight datasets from different domains show that our method outperforms previous attribute injection methods and achieves state-of-the-art performance on various datasets.