# ResidualTransformer: Residual Low-Rank Learning with Weight-Sharing for Transformer Layers

arXiv: https://arxiv.org/abs/2310.02489 · HTML: https://mlsanity.com/paper/2310.02489/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset](https://mlsanity.com/paper/2010.11395/) (2020)
- [Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer](https://mlsanity.com/paper/1910.13923/) (2019)
- [4-bit Conformer with Native Quantization Aware Training for Speech Recognition](https://mlsanity.com/paper/2203.15952/) (2022)
- [Wake Word Detection with Streaming Transformers](https://mlsanity.com/paper/2102.04488/) (2021)
- [Extremely Low Footprint End-to-End ASR System for Smart Device](https://mlsanity.com/paper/2104.05784/) (2021)
- [EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models](https://mlsanity.com/paper/2209.02341/) (2022)
- [Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models](https://mlsanity.com/paper/2303.08343/) (2023)

## Built on by (most cited first, 4 of 4)

- [Chain and Causal Attention for Efficient Entity Tracking](https://mlsanity.com/paper/2410.05565/) (2024)
- [DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights](https://mlsanity.com/paper/2501.18596/) (2025)
- [Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models](https://mlsanity.com/paper/2502.01709/) (2025)
- [CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer](https://mlsanity.com/paper/2511.14111/) (2025)

## Abstract (arXiv)

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in the device memory is a demanding challenge. In this paper, we aim to reduce model size by reparameterizing model weights across Transformer encoder layers and assuming a special weight composition and structure. More specifically, inspired by ResNet and the more recent LoRA work, we propose an approach named ResidualTransformer, where each weight matrix in a Transformer layer comprises 1) a shared full-rank component with its adjacent layers, and 2) a unique low-rank component to itself. The low-rank matrices only account for a small amount of model size increase. In addition, we add diagonal weight matrices to improve modeling capacity of the low-rank matrices. Experiments of our 10k-hour speech recognition and speech translation tasks show that the Transformer encoder size can be reduced by ~3X with very slight performance degradation.