NorBERT: NetwOrk Representations through BERT for Network Analysis and Management

TL;DR

This paper introduces NorBERT, a BERT-based model adapted for network analysis that learns meaningful embeddings for domain names, enabling effective generalization across different network environments.

Contribution

It adapts NLP pre-training techniques to network data, creating a model that produces robust, environment-independent network representations for various tasks.

Findings

Embeddings improve network task performance.

Models generalize well to unseen environments.

Effective for multiple network analysis tasks.

Abstract

Deep neural network models have been very successfully applied to Natural Language Processing (NLP) and Image based tasks. Their application to network analysis and management tasks is just recently being pursued. Our interest is in producing deep models that can be effectively generalized to perform well on multiple network tasks in different environments. A major challenge is that traditional deep models often rely on categorical features, but cannot handle unseen categorical values. One method for dealing with such problems is to learn contextual embeddings for categorical variables used by deep networks to improve their performance. In this paper, we adapt the NLP pre-training technique and associated deep model BERT to learn semantically meaningful numerical representations (embeddings) for Fully Qualified Domain Names (FQDNs) used in communication networks. We show through a series of experiments that such an approach can be used to generate models that maintain their effectiveness when applied to environments other than the one in which they were trained.