# Forgetting, plasticity, and co-observation: a third facet of continual learning

arXiv: https://arxiv.org/abs/2608.18803 · HTML: https://mlsanity.com/paper/2608.18803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance](https://mlsanity.com/paper/2403.16952/) (2024)
- [SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model](https://mlsanity.com/paper/2303.05118/) (2023)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)
- [Simple and Scalable Strategies to Continually Pre-train Large Language Models](https://mlsanity.com/paper/2403.08763/) (2024)
- [Representational Continuity for Unsupervised Continual Learning](https://mlsanity.com/paper/2110.06976/) (2021)
- [A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning](https://mlsanity.com/paper/2009.01797/) (2020)
- [Probing Representation Forgetting in Supervised and Unsupervised Continual Learning](https://mlsanity.com/paper/2203.13381/) (2022)
- [Computationally Budgeted Continual Learning: What Does Matter?](https://mlsanity.com/paper/2303.11165/) (2023)
- [Continual Learning: Applications and the Road Forward](https://mlsanity.com/paper/2311.11908/) (2023)
- [A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning](https://mlsanity.com/paper/2210.04428/) (2022)
- [Avalanche: A PyTorch Library for Deep Continual Learning](https://mlsanity.com/paper/2302.01766/) (2023)

## Abstract (arXiv)

Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two issues cannot fully explain the performance gap between naive sequential training and offline joint training. In this paper, we highlight data co-observation as a distinct factor influencing continual learning performance. By decoupling the constraints of separate data access from stability and plasticity, we systematically investigate the representational benefits gained by observing training data together. Empirically, we demonstrate a consistent performance difference between joint and separate training across both supervised and self-supervised paradigms in generic data-incremental "chunking" scenarios, whilst mitigating forgetting and controlling for plasticity. Our findings indicate that simultaneous observation of training data (co-observation) yields benefits to the learner's generalization that extend well beyond mere knowledge retention, and that this effect does not require a specific continual distribution shift. Furthermore, we contextualize prominent continual learning mechanisms through this lens: while distillation-based approaches act only as effective knowledge retention mechanisms, our results suggest that the empirical success of memory replay goes beyond the mitigation of forgetting, actively reintroducing the benefits of data co-observation into the learning process.