Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sarkar, Aishwarya, Ghosh, Sayan, Tallent, Nathan, Chadha, Aman, Roosta, Tanya, Jannesari, Ali
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911472913743872
author Sarkar, Aishwarya
Ghosh, Sayan
Tallent, Nathan
Chadha, Aman
Roosta, Tanya
Jannesari, Ali
author_facet Sarkar, Aishwarya
Ghosh, Sayan
Tallent, Nathan
Chadha, Aman
Roosta, Tanya
Jannesari, Ali
contents Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex's neighbors to a fixed distance. Because large input graphs are distributed, training requires frequent irregular communication that stalls forward progress. Moreover, fetched data changes with graph, graph distribution, sample and batch parameters, and caching polices. Consequently, any static prefetching method will miss crucial opportunities to adapt to different dynamic conditions. In this paper, we introduce Rudder, a software module embedded in the state-of-the-art AWS DistDGL framework, to autonomously prefetch remote nodes and minimize communication. Rudder's adaptation contrasts with both standard heuristics and traditional ML classifiers. We observe that the generative AI found in contemporary Large Language Models (LLMs) exhibits emergent properties like In-Context Learning (ICL) for zero-shot tasks, with logical multi-step reasoning. We find this behavior well-suited for adaptive control even with substantial undertraining. Evaluations using standard datasets and unseen configurations on the NERSC Perlmutter supercomputer show up to 91% improvement in end-to-end training performance over baseline DistDGL (no prefetching), and an 82% improvement over static prefetching, reducing communication by over 50%. Our code is available at https://github.com/aishwaryyasarkar/rudder-llm-agent.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23556
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents
Sarkar, Aishwarya
Ghosh, Sayan
Tallent, Nathan
Chadha, Aman
Roosta, Tanya
Jannesari, Ali
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Performance
Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex's neighbors to a fixed distance. Because large input graphs are distributed, training requires frequent irregular communication that stalls forward progress. Moreover, fetched data changes with graph, graph distribution, sample and batch parameters, and caching polices. Consequently, any static prefetching method will miss crucial opportunities to adapt to different dynamic conditions. In this paper, we introduce Rudder, a software module embedded in the state-of-the-art AWS DistDGL framework, to autonomously prefetch remote nodes and minimize communication. Rudder's adaptation contrasts with both standard heuristics and traditional ML classifiers. We observe that the generative AI found in contemporary Large Language Models (LLMs) exhibits emergent properties like In-Context Learning (ICL) for zero-shot tasks, with logical multi-step reasoning. We find this behavior well-suited for adaptive control even with substantial undertraining. Evaluations using standard datasets and unseen configurations on the NERSC Perlmutter supercomputer show up to 91% improvement in end-to-end training performance over baseline DistDGL (no prefetching), and an 82% improvement over static prefetching, reducing communication by over 50%. Our code is available at https://github.com/aishwaryyasarkar/rudder-llm-agent.
title Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Performance
url https://arxiv.org/abs/2602.23556