# A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes

arXiv: https://arxiv.org/abs/2009.06876 · HTML: https://mlsanity.com/paper/2009.06876/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Visual Analytics For Machine Learning: A Data Perspective Survey](https://mlsanity.com/paper/2307.07712/) (2023)
- [VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks](https://mlsanity.com/paper/2110.13252/) (2021)
- [Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference](https://mlsanity.com/paper/2404.03085/) (2024)
- [Interactive Analysis of CNN Robustness](https://mlsanity.com/paper/2110.07667/) (2021)
- [SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation](https://mlsanity.com/paper/2109.11801/) (2021)
- [Visual Analysis of Neural Architecture Spaces for Summarizing Design Principles](https://mlsanity.com/paper/2208.09665/) (2022)
- [Privacy-preserving Graph Analytics: Secure Generation and Federated Learning](https://mlsanity.com/paper/2207.00048/) (2022)
- [TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic](https://mlsanity.com/paper/2403.04812/) (2024)
- [A Comparative Visual Analytics Framework for Evaluating Evolutionary Processes in Multi-objective Optimization](https://mlsanity.com/paper/2308.05640/) (2023)

## Abstract (arXiv)

Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in reusing existing labels from similar application domains. Transfer Learning is intended to relax this assumption by modeling relationships between domains, and is often applied in deep learning applications to reduce the demand for labeled data and training time. Despite recent advances in exploring deep learning models with visual analytics tools, little work has explored the issue of explaining and diagnosing the knowledge transfer process between deep learning models. In this paper, we present a visual analytics framework for the multi-level exploration of the transfer learning processes when training deep neural networks. Our framework establishes a multi-aspect design to explain how the learned knowledge from the existing model is transferred into the new learning task when training deep neural networks. Based on a comprehensive requirement and task analysis, we employ descriptive visualization with performance measures and detailed inspections of model behaviors from the statistical, instance, feature, and model structure levels. We demonstrate our framework through two case studies on image classification by fine-tuning AlexNets to illustrate how analysts can utilize our framework.