# Finding Materialized Models for Model Reuse

arXiv: https://arxiv.org/abs/2110.06532 · HTML: https://mlsanity.com/paper/2110.06532/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 67 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [Improved Residual Networks for Image and Video Recognition](https://mlsanity.com/paper/2004.04989/) (2020)
- [Adaptive Transfer Learning on Graph Neural Networks](https://mlsanity.com/paper/2107.08765/) (2021)
- [Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization](https://mlsanity.com/paper/2108.00219/) (2021)
- [VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition](https://mlsanity.com/paper/2107.08861/) (2021)
- [How Transferable are Neural Networks in NLP Applications?](https://mlsanity.com/paper/1603.06111/) (2016)
- [Accelerating Recommendation System Training by Leveraging Popular Choices](https://mlsanity.com/paper/2103.00686/) (2021)
- [PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models](https://mlsanity.com/paper/2002.11791/) (2020)
- [ModelHub: Towards Unified Data and Lifecycle Management for Deep Learning](https://mlsanity.com/paper/1611.06224/) (2016)
- [Tuple-oriented Compression for Large-scale Mini-batch Stochastic Gradient Descent](https://mlsanity.com/paper/1702.06943/) (2017)
- [Revisiting Reuse in Main Memory Database Systems](https://mlsanity.com/paper/1608.05678/) (2016)

## Abstract (arXiv)

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 textsfMMQ, 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, textsfMMQ 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 textsfMMQ (textsfI-MMQ), which significantly reduces the query time while retaining the query performance of textsfMMQ. Extensive experiments on a range of practical model reuse workloads demonstrate the effectiveness and efficiency of textsfMMQ.