.png){kind=icon}
.png){kind=icon}
Return
Finding Materialized Models for Model Reuse
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2023.3270923.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 suitablemetric tomeasure the target-related knowledge of materialized models. To address this, we present MMQ, a source-data free, general, efficient, and effective materialized model query framework. It uses a Gaussian mixture-based metric called separation degree to rankmaterialized models. For each materialized model, 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 thematerialized model. Moreover, we propose an improved MMQ (I-MMQ), which significantly reduces the query time while retaining the query performance of MMQ. Extensive experiments on a range of practical model reuse workloads demonstrate the effectiveness and efficiency of MMQ.
Keywords:
Materialized model query
model management
model reuse
transfer learning
Journal
IF:
10.4
Papers:
6.7K
Citations:
3.2W