NOMAD -- Navigating Optimal Model Application to Datastreams

TL;DR

NOMAD is an adaptive framework that optimizes real-time multiclass classification by dynamically constructing model chains, reducing computational costs while maintaining high classification quality across diverse data streams.

Contribution

It introduces a novel, utility-based model chaining approach inspired by database query techniques, with a formal safety mechanism and dynamic belief updates for data stream classification.

Findings

Significant computational savings over static approaches

Maintains classification quality comparable to the most accurate models

Effective across multiple datasets and model configurations

Abstract

NOMAD (Navigating Optimal Model Application for Datastreams) is an intelligent framework for data enrichment during ingestion that optimizes realtime multiclass classification by dynamically constructing model chains, i.e ,sequences of machine learning models with varying cost-quality tradeoffs, selected via a utilitybased criterion. Inspired by predicate ordering techniques from database query processing, NOMAD leverages cheaper models as initial filters, proceeding to more expensive models only when necessary, while guaranteeing classification quality remains comparable to a designated role model through a formal chain safety mechanism. It employs a dynamic belief update strategy to adapt model selection based on per event predictions and shifting data distributions, and extends to scenarios with dependent models such as earlyexit DNNs and stacking ensembles. Evaluation across multiple datasets demonstrates that NOMAD achieves significant computational savings compared to static and naive approaches while maintaining classification quality comparable to that achieved by the most accurate (and often the most expensive) model.