# Lifelong Learning of Compositional Structures

arXiv: https://arxiv.org/abs/2007.07732 · HTML: https://mlsanity.com/paper/2007.07732/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 30 of 35)

- [Continual Learning via Local Module Composition](https://mlsanity.com/paper/2111.07736/) (2021)
- [Continual Learning with Foundation Models: An Empirical Study of Latent Replay](https://mlsanity.com/paper/2205.00329/) (2022)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Modular Lifelong Reinforcement Learning via Neural Composition](https://mlsanity.com/paper/2207.00429/) (2022)
- [DualNet: Continual Learning, Fast and Slow](https://mlsanity.com/paper/2110.00175/) (2021)
- [LeanAgent: Lifelong Learning for Formal Theorem Proving](https://mlsanity.com/paper/2410.06209/) (2024)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Optimizing Reusable Knowledge for Continual Learning via Metalearning](https://mlsanity.com/paper/2106.05390/) (2021)
- [Task-Aware Information Routing from Common Representation Space in Lifelong Learning](https://mlsanity.com/paper/2302.11346/) (2023)
- [Towards Lifelong Learning of End-to-end ASR](https://mlsanity.com/paper/2104.01616/) (2021)
- [CompoSuite: A Compositional Reinforcement Learning Benchmark](https://mlsanity.com/paper/2207.04136/) (2022)
- [Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges](https://mlsanity.com/paper/2311.18044/) (2023)
- [A Survey of Continual Reinforcement Learning](https://mlsanity.com/paper/2506.21872/) (2025)
- [Embodied Lifelong Learning for Task and Motion Planning](https://mlsanity.com/paper/2307.06870/) (2023)
- [Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation](https://mlsanity.com/paper/2205.09029/) (2022)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning](https://mlsanity.com/paper/2304.05288/) (2023)
- [Continual Learning for Predictive Maintenance: Overview and Challenges](https://mlsanity.com/paper/2301.12467/) (2023)
- [Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks](https://mlsanity.com/paper/2305.10997/) (2023)
- [Entropy-based Stability-Plasticity for Lifelong Learning](https://mlsanity.com/paper/2204.09517/) (2022)
- [Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Data](https://mlsanity.com/paper/2112.13215/) (2021)
- [SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries](https://mlsanity.com/paper/2206.13720/) (2022)
- [Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing](https://mlsanity.com/paper/2210.15051/) (2022)
- [The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning](https://mlsanity.com/paper/2302.10887/) (2023)
- [Visually Grounded Continual Language Learning with Selective Specialization](https://mlsanity.com/paper/2310.15571/) (2023)
- [Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning](https://mlsanity.com/paper/2403.05066/) (2024)
- [RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks](https://mlsanity.com/paper/2411.16870/) (2024)
- [Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems](https://mlsanity.com/paper/2506.05577/) (2025)
- [Continual Learning, Fast and Slow](https://mlsanity.com/paper/2209.02370/) (2022)
- [Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis](https://mlsanity.com/paper/2305.18402/) (2023)

## Abstract (arXiv)

A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and adequately reuse them in novel combinations for solving different yet structurally related problems. Learning such compositional structures has been a significant challenge for artificial systems, due to the combinatorial nature of the underlying search problem. To date, research into compositional learning has largely proceeded separately from work on lifelong or continual learning. We integrate these two lines of work to present a general-purpose framework for lifelong learning of compositional structures that can be used for solving a stream of related tasks. Our framework separates the learning process into two broad stages: learning how to best combine existing components in order to assimilate a novel problem, and learning how to adapt the set of existing components to accommodate the new problem. This separation explicitly handles the trade-off between the stability required to remember how to solve earlier tasks and the flexibility required to solve new tasks, as we show empirically in an extensive evaluation.