# Modular Deep Learning

arXiv: https://arxiv.org/abs/2302.11529 · HTML: https://mlsanity.com/paper/2302.11529/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- Builds on 256 of its 329 references that are in the map.
- First posted on arXiv 22 Feb 2023.

## Builds on (most cited first, 30 of 256)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)

## Built on by (most cited first, 30 of 83)

- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [Composing Parameter-Efficient Modules with Arithmetic Operations](https://mlsanity.com/paper/2306.14870/) (2023)
- [Soft Merging of Experts with Adaptive Routing](https://mlsanity.com/paper/2306.03745/) (2023)
- [Towards Modular LLMs by Building and Reusing a Library of LoRAs](https://mlsanity.com/paper/2405.11157/) (2024)
- [A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning](https://mlsanity.com/paper/2408.07057/) (2024)
- [Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability](https://mlsanity.com/paper/2305.08746/) (2023)
- [Gradient Routing: Masking Gradients to Localize Computation in Neural Networks](https://mlsanity.com/paper/2410.04332/) (2024)
- [Elastic Weight Removal for Faithful and Abstractive Dialogue Generation](https://mlsanity.com/paper/2303.17574/) (2023)
- [Denoising Task Routing for Diffusion Models](https://mlsanity.com/paper/2310.07138/) (2023)
- [HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts](https://mlsanity.com/paper/2402.12656/) (2024)
- [Modular Blind Video Quality Assessment](https://mlsanity.com/paper/2402.19276/) (2024)
- [Configurable Foundation Models: Building LLMs from a Modular Perspective](https://mlsanity.com/paper/2409.02877/) (2024)
- [Romanization-based Large-scale Adaptation of Multilingual Language Models](https://mlsanity.com/paper/2304.08865/) (2023)
- [Fine-tuning Large Language Models with Sequential Instructions](https://mlsanity.com/paper/2403.07794/) (2024)
- [ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization](https://mlsanity.com/paper/2311.13171/) (2023)
- [A Second-Order Perspective on Model Compositionality and Incremental Learning](https://mlsanity.com/paper/2405.16350/) (2024)
- [A Survey of Continual Reinforcement Learning](https://mlsanity.com/paper/2506.21872/) (2025)
- [Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection](https://mlsanity.com/paper/2409.15844/) (2024)
- [A Complexity-Based Theory of Compositionality](https://mlsanity.com/paper/2410.14817/) (2024)
- [Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs](https://mlsanity.com/paper/2512.05648/) (2025)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization](https://mlsanity.com/paper/2506.13331/) (2025)
- [Bolmo: Byteifying the Next Generation of Language Models](https://mlsanity.com/paper/2512.15586/) (2025)
- [Physics of Skill Learning](https://mlsanity.com/paper/2501.12391/) (2025)
- [Modular Domain Adaptation for Conformer-Based Streaming ASR](https://mlsanity.com/paper/2305.13408/) (2023)
- [Adaptivity and Modularity for Efficient Generalization Over Task Complexity](https://mlsanity.com/paper/2310.08866/) (2023)
- [MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters](https://mlsanity.com/paper/2311.04251/) (2023)
- [The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights](https://mlsanity.com/paper/2405.01345/) (2024)
- [ELICIT: LLM Augmentation via External In-Context Capability](https://mlsanity.com/paper/2410.09343/) (2024)
- [Distilling Efficient Language-Specific Models for Cross-Lingual Transfer](https://mlsanity.com/paper/2306.01709/) (2023)

## Abstract (arXiv)

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop models that specialise towards multiple tasks without incurring negative interference and that generalise systematically to non-identically distributed tasks. Modular deep learning has emerged as a promising solution to these challenges. In this framework, units of computation are often implemented as autonomous parameter-efficient modules. Information is conditionally routed to a subset of modules and subsequently aggregated. These properties enable positive transfer and systematic generalisation by separating computation from routing and updating modules locally. We offer a survey of modular architectures, providing a unified view over several threads of research that evolved independently in the scientific literature. Moreover, we explore various additional purposes of modularity, including scaling language models, causal inference, programme induction, and planning in reinforcement learning. Finally, we report various concrete applications where modularity has been successfully deployed such as cross-lingual and cross-modal knowledge transfer. Related talks and projects to this survey, are available at https://www.modulardeeplearning.com/.