A new hope for network model generalization
Dietmüller, Alexander, Ray, Siddhant, Jacob, Romain, Vanbever, Laurent
–arXiv.org Artificial Intelligence
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, though it calls for a lot of future research.
arXiv.org Artificial Intelligence
Oct-18-2022
- Country:
- North America > United States
- Texas > Travis County
- Austin (0.05)
- New York > New York County
- New York City (0.05)
- Massachusetts > Suffolk County
- Boston (0.04)
- California > Los Angeles County
- Los Angeles (0.04)
- Texas > Travis County
- Europe
- North America > United States
- Genre:
- Research Report > Experimental Study (0.48)
- Industry:
- Information Technology > Services (0.59)
- Telecommunications > Networks (0.47)
- Technology: