# Learn-Prune-Share for Lifelong Learning

arXiv: https://arxiv.org/abs/2012.06956 · HTML: https://mlsanity.com/paper/2012.06956/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2020.

## Built on by (most cited first, 30 of 32)

- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [CLIP model is an Efficient Continual Learner](https://mlsanity.com/paper/2210.03114/) (2022)
- [SparCL: Sparse Continual Learning on the Edge](https://mlsanity.com/paper/2209.09476/) (2022)
- [Introducing Language Guidance in Prompt-based Continual Learning](https://mlsanity.com/paper/2308.15827/) (2023)
- [AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning](https://mlsanity.com/paper/2305.11488/) (2023)
- [Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation](https://mlsanity.com/paper/2411.05663/) (2024)
- [OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2402.04129/) (2024)
- [Multimodal Parameter-Efficient Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2303.04751/) (2023)
- [DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning](https://mlsanity.com/paper/2305.00380/) (2023)
- [Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention](https://mlsanity.com/paper/2312.15033/) (2023)
- [Continual Learning in the Frequency Domain](https://mlsanity.com/paper/2410.06645/) (2024)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Theoretical Understanding of the Information Flow on Continual Learning Performance](https://mlsanity.com/paper/2204.12010/) (2022)
- [STAR: Stability-Inducing Weight Perturbation for Continual Learning](https://mlsanity.com/paper/2503.01595/) (2025)
- [Brain-inspired continual pre-trained learner via silent synaptic consolidation](https://mlsanity.com/paper/2410.05899/) (2024)
- [Neural Network-based OFDM Receiver for Resource Constrained IoT Devices](https://mlsanity.com/paper/2205.06159/) (2022)
- [C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor](https://mlsanity.com/paper/2508.01311/) (2025)
- [Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging](https://mlsanity.com/paper/2310.18639/) (2023)
- [Prompt Customization for Continual Learning](https://mlsanity.com/paper/2404.18060/) (2024)
- [LVP-CLIP:Revisiting CLIP for Continual Learning with Label Vector Pool](https://mlsanity.com/paper/2412.05840/) (2024)
- [Investigating the Impact of Weight Sharing Decisions on Knowledge Transfer in Continual Learning](https://mlsanity.com/paper/2311.09506/) (2023)
- [Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning](https://mlsanity.com/paper/2406.19753/) (2024)
- [LightCL: Compact Continual Learning with Low Memory Footprint For Edge Device](https://mlsanity.com/paper/2407.10545/) (2024)
- [CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation](https://mlsanity.com/paper/2502.17429/) (2025)
- [Efficient Continual Learning through Frequency Decomposition and Integration](https://mlsanity.com/paper/2503.22175/) (2025)
- [ELC: Evidential Lifelong Classifier for Uncertainty Aware Radar Pulse Classification](https://mlsanity.com/paper/2604.06958/) (2026)
- [Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2601.21341/) (2026)
- [Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2601.21345/) (2026)
- [From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2602.20911/) (2026)

## Abstract (arXiv)

In lifelong learning, we wish to maintain and update a model (e.g., a neural network classifier) in the presence of new classification tasks that arrive sequentially. In this paper, we propose a learn-prune-share (LPS) algorithm which addresses the challenges of catastrophic forgetting, parsimony, and knowledge reuse simultaneously. LPS splits the network into task-specific partitions via an ADMM-based pruning strategy. This leads to no forgetting, while maintaining parsimony. Moreover, LPS integrates a novel selective knowledge sharing scheme into this ADMM optimization framework. This enables adaptive knowledge sharing in an end-to-end fashion. Comprehensive experimental results on two lifelong learning benchmark datasets and a challenging real-world radio frequency fingerprinting dataset are provided to demonstrate the effectiveness of our approach. Our experiments show that LPS consistently outperforms multiple state-of-the-art competitors.