LLM-Sketch: Enhancing Network Sketches with LLM
This work addresses network operations by improving sketch-based stream mining, though it appears incremental as it builds on existing machine learning approaches for sketches.
The paper tackles the problem of network stream mining by proposing LLM-Sketch, a method that enhances sketch accuracy using large language models and a two-tier data structure, resulting in a 7.5x accuracy improvement over state-of-the-art methods.
Network stream mining is fundamental to many network operations. Sketches, as compact data structures that offer low memory overhead with bounded accuracy, have emerged as a promising solution for network stream mining. Recent studies attempt to optimize sketches using machine learning; however, these approaches face the challenges of lacking adaptivity to dynamic networks and incurring high training costs. In this paper, we propose LLM-Sketch, based on the insight that fields beyond the flow IDs in packet headers can also help infer flow sizes. By using a two-tier data structure and separately recording large and small flows, LLM-Sketch improves accuracy while minimizing memory usage. Furthermore, it leverages fine-tuned large language models (LLMs) to reliably estimate flow sizes. We evaluate LLM-Sketch on three representative tasks, and the results demonstrate that LLM-Sketch outperforms state-of-the-art methods by achieving a $7.5\times$ accuracy improvement.