# Generative Continual Concept Learning

arXiv: https://arxiv.org/abs/1906.03744 · HTML: https://mlsanity.com/paper/1906.03744/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2019.

## Built on by (most cited first, 26 of 26)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Detection and Continual Learning of Novel Face Presentation Attacks](https://mlsanity.com/paper/2108.12081/) (2021)
- [Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations](https://mlsanity.com/paper/2203.06514/) (2022)
- [Cognitively Inspired Learning of Incremental Drifting Concepts](https://mlsanity.com/paper/2110.04662/) (2021)
- [Unsupervised Model Adaptation for Source-free Segmentation of Medical Images](https://mlsanity.com/paper/2211.00807/) (2022)
- [Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation](https://mlsanity.com/paper/2303.14423/) (2023)
- [BrainWash: A Poisoning Attack to Forget in Continual Learning](https://mlsanity.com/paper/2311.11995/) (2023)
- [Sample-Efficient Learning of Novel Visual Concepts](https://mlsanity.com/paper/2306.09482/) (2023)
- [Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks](https://mlsanity.com/paper/2401.15275/) (2024)
- [Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process](https://mlsanity.com/paper/2108.12278/) (2021)
- [FFNB: Forgetting-Free Neural Blocks for Deep Continual Visual Learning](https://mlsanity.com/paper/2111.11366/) (2021)
- [Is Multi-Task Learning an Upper Bound for Continual Learning?](https://mlsanity.com/paper/2210.14797/) (2022)
- [Leveraging Relational Information for Learning Weakly Disentangled Representations](https://mlsanity.com/paper/2205.10056/) (2022)
- [History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2305.18675/) (2023)
- [Improved Region Proposal Network for Enhanced Few-Shot Object Detection](https://mlsanity.com/paper/2308.07535/) (2023)
- [Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation](https://mlsanity.com/paper/2107.01598/) (2021)
- [Encoding Binary Concepts in the Latent Space of Generative Models for Enhancing Data Representation](https://mlsanity.com/paper/2303.12255/) (2023)
- [CovarNav: Machine Unlearning via Model Inversion and Covariance Navigation](https://mlsanity.com/paper/2311.12999/) (2023)
- [Cognitively Inspired Cross-Modal Data Generation Using Diffusion Models](https://mlsanity.com/paper/2305.18433/) (2023)
- [Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay](https://mlsanity.com/paper/2402.00580/) (2024)
- [Employing chunk size adaptation to overcome concept drift](https://mlsanity.com/paper/2110.12881/) (2021)
- [Robust Internal Representations for Domain Generalization](https://mlsanity.com/paper/2309.15522/) (2023)
- [Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations](https://mlsanity.com/paper/2401.01035/) (2024)
- [Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2401.01042/) (2024)
- [Unsupervised Federated Domain Adaptation for Segmentation of MRI Images](https://mlsanity.com/paper/2401.02941/) (2024)
- [Caption, Create, Continue: Continual Learning with Pre-trained Generative Vision-Language Models](https://mlsanity.com/paper/2409.17806/) (2024)

## Abstract (arXiv)

After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for current Artificial Intelligence algorithms as persistent model retraining is necessary. Inspired by the Parallel Distributed Processing learning and the Complementary Learning Systems theories, we develop a computational model that is able to expand its previously learned concepts efficiently to new domains using a few labeled samples. We couple the new form of a concept to its past learned forms in an embedding space for effective continual learning. Doing so, a generative distribution is learned such that it is shared across the tasks in the embedding space and models the abstract concepts. This procedure enables the model to generate pseudo-data points to replay the past experience to tackle catastrophic forgetting.