Finding Materialized Models for Model Reuse

TL;DR

This paper introduces extsf{MMQ} and extsf{I-MMQ}, novel frameworks for efficiently finding the most suitable materialized models for reuse without needing source data, using a Gaussian mixture-based metric.

Contribution

It proposes a source-data free, general, and efficient framework for materialized model query that measures target-related knowledge using a novel separation degree metric.

Findings

ffective in practical model reuse workloads

Significantly reduces query time with extsf{I-MMQ}

Outperforms existing methods in accuracy and efficiency

Abstract

Materialized model query aims to find the most appropriate materialized model as the initial model for model reuse. It is the precondition of model reuse, and has recently attracted much attention. {Nonetheless, the existing methods suffer from the need to provide source data, limited range of applications, and inefficiency since they do not construct a suitable metric to measure the target-related knowledge of materialized models. To address this, we present \textsf{MMQ}, a source-data free, general, efficient, and effective materialized model query framework.} It uses a Gaussian mixture-based metric called separation degree to rank materialized models. For each materialized model, \textsf{MMQ} first vectorizes the samples in the target dataset into probability vectors by directly applying this model, then utilizes Gaussian distribution to fit for each class of probability vectors, and finally uses separation degree on the Gaussian distributions to measure the target-related knowledge of the materialized model. Moreover, we propose an improved \textsf{MMQ} (\textsf{I-MMQ}), which significantly reduces the query time while retaining the query performance of \textsf{MMQ}. Extensive experiments on a range of practical model reuse workloads demonstrate the effectiveness and efficiency of \textsf{MMQ}.