A New Hope for Network Model Generalization
Abstract
Generalizing machine learning (ML) models for network traffic dynamics tends to be considered a lost cause. Hence for every new task, we design new models and train them on model-specific datasets closely mimicking the deployment environments. Yet, an ML architecture called Transformer has enabled previously unimaginable generalization in other domains. Nowadays, one can download a model pre-trained on massive datasets and only fine-tune it for a specific task and context with comparatively little time and data. These fine-tuned models are now state-of-the-art for many benchmarks. We believe this progress could translate to networking and propose a Network Traffic Transformer (NTT), a transformer adapted to learn network dynamics from packet traces. Our initial results are promising: NTT seems able to generalize to new prediction tasks and environments. This study suggests there is still hope for generalization through future research.
Research Area: Network Analysis and Reasoning
People
Talk
BibTex
@inproceedings{dietmüller2022network,
author = {Dietm{\"{u}}ller, Alexander and Ray, Siddhant and Jacob, Romain and Vanbever, Laurent},
title = {{A New Hope for Network Model Generalization}},
booktitle = {HotNets '22: Proceedings of the 21st ACM Workshop on Hot Topics in Networks},
address = {Austin, TX, USA},
year = 2022,
month = nov,
publisher = {Association for Computing Machinery},
doi = {10.1145/3563766.3564104},
url = {https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/577569/main.pdf}
}Research Collection: 20.500.11850/577569
Slide Sources: https://gitlab.ethz.ch/projects/41272