AI News HubLIVE
Original source2 min read

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

arXiv:2609.00078v1 Announce Type: new Abstract: 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.

SourcearXiv Machine LearningAuthor: Xingran Chen, Rohit Bhagat, Ghadir Ayache, Rawad Bitar, Yanmin Gong, Salim El Rouayheb

-->

[Submitted on 31 Aug 2026]

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

View a PDF of the paper titled RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks, by Xingran Chen and 5 other authors

View PDF HTML (experimental)

Abstract: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.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.00078 [cs.LG]

(or arXiv:2609.00078v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.00078

arXiv-issued DOI via DataCite

Submission history

From: Xingran Chen [view email] [v1] Mon, 31 Aug 2026 08:24:24 UTC (1,543 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks, by Xingran Chen and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)