NetLLM: Adapting Large Language Models for Networking

Abstract

Many networking tasks now employ deep learning (DL) to solve complex prediction and optimization problems. However, current design philosophy of DL-based algorithms entails intensive engineering overhead due to the manual design of deep neural networks (DNNs) for different networking tasks. Besides, DNNs tend to achieve poor generalization performance on unseen data distributions/environments. Motivated by the recent success of large language models (LLMs), this work studies the LLM adaptation for networking to explore a more sustainable design philosophy. With the powerful pre-trained knowledge, the LLM is promising to serve as the foundation model to achieve "one model for all tasks" with even better performance and stronger generalization. In pursuit of this vision, we present NetLLM, the first framework that provides a coherent design to harness the powerful capabilities of LLMs with low efforts to solve networking problems. Specifically, NetLLM empowers the LLM to effectively process multimodal data in networking and efficiently generate task-specific answers. Besides, NetLLM drastically reduces the costs of fine-tuning the LLM to acquire domain knowledge for networking. Across three networking-related use cases - viewport prediction, adaptive bitrate streaming and cluster job scheduling, we showcase that the NetLLM-adapted LLM significantly outperforms state-of-the-art algorithms.

This paper has been accepted by ACM SIGCOMM 2024. DOI: https://doi.org/10.1145/3651890.3672268

References in corpus (7)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification
• Decision Transformer: Reinforcement Learning via Sequence Modeling
• Discrimination-aware Network Pruning for Deep Model Compression
• Offline Reinforcement Learning as One Big Sequence Modeling Problem
• Advancing Model Pruning via Bi-level Optimization

Cited by in corpus (6)

• Respond to Change with Constancy: Instruction-tuning with LLM for Non-I.I.D. Network Traffic Classification
• Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies
• Beyond Interpretability: Exploring the Comprehensibility of Adaptive Video Streaming through Large Language Models
• ReGAIN: Retrieval-Grounded AI Framework for Network Traffic Analysis
• On Harnessing Idle Compute at the Edge for Foundation Model Training
• Algorithmic Data Minimization for Machine Learning over Internet-of-Things Data Streams