# Ex-Model: Continual Learning from a Stream of Trained Models

arXiv: https://arxiv.org/abs/2112.06511 · HTML: https://mlsanity.com/paper/2112.06511/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [FearNet: Brain-Inspired Model for Incremental Learning](https://mlsanity.com/paper/1711.10563/) (2017)
- [Class-incremental Learning via Deep Model Consolidation](https://mlsanity.com/paper/1903.07864/) (2019)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Zero-Shot Knowledge Distillation in Deep Networks](https://mlsanity.com/paper/1905.08114/) (2019)
- [Continuous Learning in Single-Incremental-Task Scenarios](https://mlsanity.com/paper/1806.08568/) (2018)
- [Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges](https://mlsanity.com/paper/1907.00182/) (2019)
- [Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis](https://mlsanity.com/paper/1909.01520/) (2019)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [A distillation-based approach integrating continual learning and federated learning for pervasive services](https://mlsanity.com/paper/2109.04197/) (2021)
- [Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay](https://mlsanity.com/paper/2106.09835/) (2021)
- [Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning](https://mlsanity.com/paper/2109.00150/) (2021)

## Built on by (most cited first, 11 of 11)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [The Future of Continual Learning in the Era of Foundation Models: Three Key Directions](https://mlsanity.com/paper/2506.03320/) (2025)
- [Practical Recommendations for Replay-based Continual Learning Methods](https://mlsanity.com/paper/2203.10317/) (2022)
- [Heterogeneous Continual Learning](https://mlsanity.com/paper/2306.08593/) (2023)
- [Continual Learning From a Stream of APIs](https://mlsanity.com/paper/2309.00023/) (2023)
- [Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning](https://mlsanity.com/paper/2303.15888/) (2023)
- [Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand Manipulation](https://mlsanity.com/paper/2404.04219/) (2024)
- [Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications](https://mlsanity.com/paper/2510.27186/) (2025)
- [CovarNav: Machine Unlearning via Model Inversion and Covariance Navigation](https://mlsanity.com/paper/2311.12999/) (2023)
- [Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning](https://mlsanity.com/paper/2301.02464/) (2023)
- [Batch Model Consolidation: A Multi-Task Model Consolidation Framework](https://mlsanity.com/paper/2305.16484/) (2023)

## Abstract (arXiv)

Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt, and generalize continually in an efficient, effective, and scalable way is fundamental for a sustainable development of Artificial Intelligent systems. However, an agent-centric view of continual learning requires learning directly from raw data, which limits the interaction between independent agents, the efficiency, and the privacy of current approaches. Instead, we argue that continual learning systems should exploit the availability of compressed information in the form of trained models. In this paper, we introduce and formalize a new paradigm named "Ex-Model Continual Learning" (ExML), where an agent learns from a sequence of previously trained models instead of raw data. We further contribute with three ex-model continual learning algorithms and an empirical setting comprising three datasets (MNIST, CIFAR-10 and CORe50), and eight scenarios, where the proposed algorithms are extensively tested. Finally, we highlight the peculiarities of the ex-model paradigm and we point out interesting future research directions.