# Model Reuse with Reduced Kernel Mean Embedding Specification

arXiv: https://arxiv.org/abs/2001.07135 · HTML: https://mlsanity.com/paper/2001.07135/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2020.

## Built on by (most cited first, 14 of 14)

- [Deep Model Fusion: A Survey](https://mlsanity.com/paper/2309.15698/) (2023)
- [Adapting to Online Label Shift with Provable Guarantees](https://mlsanity.com/paper/2207.02121/) (2022)
- [Learnware: Small Models Do Big](https://mlsanity.com/paper/2210.03647/) (2022)
- [Which Model to Transfer? A Survey on Transferability Estimation](https://mlsanity.com/paper/2402.15231/) (2024)
- [FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion](https://mlsanity.com/paper/2406.03280/) (2024)
- [Beimingwu: A Learnware Dock System](https://mlsanity.com/paper/2401.14427/) (2024)
- [Improving Heterogeneous Model Reuse by Density Estimation](https://mlsanity.com/paper/2305.13871/) (2023)
- [Vision-Language Model Selection and Reuse for Downstream Adaptation](https://mlsanity.com/paper/2501.18271/) (2025)
- [Learnware of Language Models: Specialized Small Language Models Can Do Big](https://mlsanity.com/paper/2505.13425/) (2025)
- [MAGIC: Achieving Superior Model Merging via Magnitude Calibration](https://mlsanity.com/paper/2512.19320/) (2025)
- [Selective Cross-Task Distillation](https://mlsanity.com/paper/2204.11526/) (2022)
- [CGI: Identifying Conditional Generative Models with Example Images](https://mlsanity.com/paper/2501.13991/) (2025)
- [Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design](https://mlsanity.com/paper/2507.15336/) (2025)
- [Learnware and AI Model Management System](https://mlsanity.com/paper/2609.11656/) (2026)

## Abstract (arXiv)

Given a publicly available pool of machine learning models constructed for various tasks, when a user plans to build a model for her own machine learning application, is it possible to build upon models in the pool such that the previous efforts on these existing models can be reused rather than starting from scratch? Here, a grand challenge is how to find models that are helpful for the current application, without accessing the raw training data for the models in the pool. In this paper, we present a two-phase framework. In the upload phase, when a model is uploading into the pool, we construct a reduced kernel mean embedding (RKME) as a specification for the model. Then in the deployment phase, the relatedness of the current task and pre-trained models will be measured based on the value of the RKME specification. Theoretical results and extensive experiments validate the effectiveness of our approach.