# RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks

arXiv: https://arxiv.org/abs/2609.00078 · HTML: https://mlsanity.com/paper/2609.00078/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations](https://mlsanity.com/paper/2409.05976/) (2024)
- [Selective Aggregation for Low-Rank Adaptation in Federated Learning](https://mlsanity.com/paper/2410.01463/) (2024)
- [On Markov Chain Gradient Descent](https://mlsanity.com/paper/1809.04216/) (2018)
- [Stochastic Gradient Descent under Markovian Sampling Schemes](https://mlsanity.com/paper/2302.14428/) (2023)
- [FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models](https://mlsanity.com/paper/2410.09432/) (2024)
- [Private Weighted Random Walk Stochastic Gradient Descent](https://mlsanity.com/paper/2009.01790/) (2020)
- [Decentralized Low-Rank Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2501.15361/) (2025)
- [FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA](https://mlsanity.com/paper/2503.11880/) (2025)
- [FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA](https://mlsanity.com/paper/2602.23638/) (2026)
- [Random Walk Learning and the Pac-Man Attack](https://mlsanity.com/paper/2508.05663/) (2025)
- [FedMomentum: Preserving LoRA Training Momentum in Federated Fine-Tuning](https://mlsanity.com/paper/2603.08014/) (2026)
- [Self-Creating Random Walks for Decentralized Learning under Pac-Man Attacks](https://mlsanity.com/paper/2601.07674/) (2026)
- [Source Anonymity for Private Random Walk Decentralized Learning](https://mlsanity.com/paper/2505.07011/) (2025)
- [SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks](https://mlsanity.com/paper/2608.10144/) (2026)

## Built on by (most cited first, 1 of 1)

- [Multi-Token Random-Walk Learning via Meeting-Triggered Information Exchange](https://mlsanity.com/paper/2610.14716/) (2026)

## Abstract (arXiv)

Parameter-efficient fine-tuning methods such as LoRA have become a standard approach for adapting large foundation models. Adopting fine-tuning to distributed settings faces several challenges. Most existing distributed LoRA methods rely on centralized aggregation, and gossip-based decentralized LoRA requires repeated synchronization among multiple model copies. Both methods incur significant communication overhead and introduce errors due to simultaneous aggregation of multiple model updates. In this paper, we take a different perspective and propose a random-walk-based LoRA fine-tuning scheme. Instead of maintaining multiple model replicas, a single model token traverses the network and is updated sequentially using local fine-tuning objectives. This design eliminates the need for global synchronization, substantially reduces communication and computation costs, and avoids aggregation errors. We provide rigorous convergence guarantees for non-convex objectives under standard assumptions. Through empirical results on multiple NLP tasks and graph topologies, we show that the proposed method achieves competitive task performance with substantially less communication and computation than gossip-based LoRA.