# Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence

arXiv: https://arxiv.org/abs/2603.08600 · HTML: https://mlsanity.com/paper/2603.08600/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges](https://mlsanity.com/paper/1907.00182/) (2019)
- [Deep Learning for Time Series Forecasting: The Electric Load Case](https://mlsanity.com/paper/1907.09207/) (2019)
- [Online Continual Learning on Sequences](https://mlsanity.com/paper/2003.09114/) (2020)
- [Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments](https://mlsanity.com/paper/2603.01695/) (2026)
- [cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series](https://mlsanity.com/paper/2603.03040/) (2026)

## Abstract (arXiv)

Concept drift, temporal dependence, and catastrophic forgetting represent major challenges when learning from data streams. While Streaming Machine Learning and Continual Learning (CL) address these issues separately, recent efforts in Streaming Continual Learning (SCL) aim to unify them. In this work, we introduce MAGIC Net, a novel SCL approach that integrates CL-inspired architectural strategies with recurrent neural networks to tame temporal dependence. MAGIC Net continuously learns, looks back at past knowledge by applying learnable masks over frozen weights, and expands its architecture when necessary. It performs all operations online, ensuring inference availability at all times. Experiments on synthetic and real-world streams show that it improves adaptation to new concepts, limits memory usage, and mitigates forgetting.