# Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning

arXiv: https://arxiv.org/abs/2304.05288 · HTML: https://mlsanity.com/paper/2304.05288/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [Reinforced Continual Learning](https://mlsanity.com/paper/1805.12369/) (2018)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [Efficient Continual Learning with Modular Networks and Task-Driven Priors](https://mlsanity.com/paper/2012.12631/) (2020)
- [Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks](https://mlsanity.com/paper/2112.10017/) (2021)
- [Continual Learning via Local Module Composition](https://mlsanity.com/paper/2111.07736/) (2021)

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

- [Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning](https://mlsanity.com/paper/2409.10956/) (2024)
- [Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration](https://mlsanity.com/paper/2403.11373/) (2024)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates](https://mlsanity.com/paper/2512.04844/) (2025)
- [Self-Regulated Neurogenesis for Online Data-Incremental Learning](https://mlsanity.com/paper/2403.14684/) (2024)
- [Not Just Object, But State: Compositional Incremental Learning without Forgetting](https://mlsanity.com/paper/2411.01739/) (2024)
- [What Can AutoML Do For Continual Learning?](https://mlsanity.com/paper/2311.11963/) (2023)
- [Algorithm Design for Continual Learning in IoT Networks](https://mlsanity.com/paper/2412.16830/) (2024)
- [A Methodology-Oriented Study of Catastrophic Forgetting in Incremental Deep Neural Networks](https://mlsanity.com/paper/2405.08015/) (2024)
- [ER-FSL: Experience Replay with Feature Subspace Learning for Online Continual Learning](https://mlsanity.com/paper/2407.12279/) (2024)
- [Unlocking [CLS] Features for Continual Post-Training](https://mlsanity.com/paper/2502.14762/) (2025)

## Abstract (arXiv)

Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and ignore the differences in the learning difficulty of different tasks. So parameter regularization methods face significant forgetting when learning a new task very different from learned tasks, and parameter allocation methods face unnecessary parameter overhead when learning simple tasks. In this paper, we propose the Parameter Allocation & Regularization (PAR), which adaptively select an appropriate strategy for each task from parameter allocation and regularization based on its learning difficulty. A task is easy for a model that has learned tasks related to it and vice versa. We propose a divergence estimation method based on the Nearest-Prototype distance to measure the task relatedness using only features of the new task. Moreover, we propose a time-efficient relatedness-aware sampling-based architecture search strategy to reduce the parameter overhead for allocation. Experimental results on multiple benchmarks demonstrate that, compared with SOTAs, our method is scalable and significantly reduces the model's redundancy while improving the model's performance. Further qualitative analysis indicates that PAR obtains reasonable task-relatedness.