# SiRA: Sparse Mixture of Low Rank Adaptation

arXiv: https://arxiv.org/abs/2311.09179 · HTML: https://mlsanity.com/paper/2311.09179/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Mixture of LoRA experts, one of 12 directions in Mixture-of-experts.
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Placed in

- Mixture-of-experts / [Mixture of LoRA experts](https://mlsanity.com/moe/mixture-of-lora-experts/)

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [Hash Layers For Large Sparse Models](https://mlsanity.com/paper/2106.04426/) (2021)
- [Conditional Computation in Neural Networks for faster models](https://mlsanity.com/paper/1511.06297/) (2015)
- [UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning](https://mlsanity.com/paper/2110.07577/) (2021)
- [Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning](https://mlsanity.com/paper/2309.05444/) (2023)
- [AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning](https://mlsanity.com/paper/2210.17451/) (2022)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [Revisiting Parameter-Efficient Tuning: Are We Really There Yet?](https://mlsanity.com/paper/2202.07962/) (2022)
- [Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers](https://mlsanity.com/paper/2303.01610/) (2023)
- [XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages](https://mlsanity.com/paper/2305.11938/) (2023)
- [Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation](https://mlsanity.com/paper/2212.07571/) (2022)

## Built on by (most cited first, 30 of 32)

- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning](https://mlsanity.com/paper/2312.12379/) (2023)
- [LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild](https://mlsanity.com/paper/2402.09997/) (2024)
- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [Model Compression and Efficient Inference for Large Language Models: A Survey](https://mlsanity.com/paper/2402.09748/) (2024)
- [Advancing Expert Specialization for Better MoE](https://mlsanity.com/paper/2505.22323/) (2025)
- [AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts](https://mlsanity.com/paper/2405.00361/) (2024)
- [Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning](https://mlsanity.com/paper/2602.00994/) (2026)
- [Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning](https://mlsanity.com/paper/2406.16989/) (2024)
- [Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning](https://mlsanity.com/paper/2501.15103/) (2025)
- [Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation](https://mlsanity.com/paper/2405.16486/) (2024)
- [Ensembles of Low-Rank Expert Adapters](https://mlsanity.com/paper/2502.00089/) (2025)
- [A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models](https://mlsanity.com/paper/2502.15828/) (2025)
- [PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning](https://mlsanity.com/paper/2407.21571/) (2024)
- [Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference](https://mlsanity.com/paper/2406.07007/) (2024)
- [Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers](https://mlsanity.com/paper/2404.09326/) (2024)
- [MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2405.18897/) (2024)
- [MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts](https://mlsanity.com/paper/2408.01505/) (2024)
- [TT-LoRA MoE: Unifying Parameter-Efficient Fine-Tuning and Sparse Mixture-of-Experts](https://mlsanity.com/paper/2504.21190/) (2025)
- [MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning](https://mlsanity.com/paper/2412.07405/) (2024)
- [MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learning](https://mlsanity.com/paper/2412.08946/) (2024)
- [MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2506.05928/) (2025)
- [A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation](https://mlsanity.com/paper/2601.22708/) (2026)
- [BoRA: Bayesian Hierarchical Low-Rank Adaption for Multi-Task Large Language Models](https://mlsanity.com/paper/2407.15857/) (2024)
- [Collaborative and Efficient Personalization with Mixtures of Adaptors](https://mlsanity.com/paper/2410.03497/) (2024)
- [Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning](https://mlsanity.com/paper/2604.01152/) (2026)
- [Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures](https://mlsanity.com/paper/2402.17934/) (2024)
- [Improving Ensemble Forecasts of Abnormally Deflecting Tropical Cyclones with Fused Atmosphere-Ocean-Terrain Data](https://mlsanity.com/paper/2603.29200/) (2026)
- [Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation](https://mlsanity.com/paper/2605.07111/) (2026)

## Abstract (arXiv)

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We found this less effective empirically using the example of LoRA that introducing more trainable parameters does not help. Motivated by this we investigate the importance of leveraging "sparse" computation and propose SiRA: sparse mixture of low rank adaption. SiRA leverages the Sparse Mixture of Expert(SMoE) to boost the performance of LoRA. Specifically it enforces the top k experts routing with a capacity limit restricting the maximum number of tokens each expert can process. We propose a novel and simple expert dropout on top of gating network to reduce the over-fitting issue. Through extensive experiments, we verify SiRA performs better than LoRA and other mixture of expert approaches across different single tasks and multitask settings.