NetLLM: Adapting Large Language Models for Networking
This addresses the problem of inefficient and non-generalizable deep learning methods for networking tasks, offering a more sustainable design philosophy, though it appears incremental as it adapts existing LLMs rather than introducing a new paradigm.
The paper tackles the high engineering overhead and poor generalization of deep learning in networking by adapting large language models (LLMs) into NetLLM, a framework that achieves 'one model for all tasks' and significantly outperforms state-of-the-art algorithms in use cases like viewport prediction, adaptive bitrate streaming, and cluster job scheduling.
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.