Research map / Continual learning / Online and replay-based
Generative Continual Concept Learning
Mohammad Rostami, Soheil Kolouri, Praveen Pilly, James McClelland
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ECLA with generative replay instead of classic backpropagation | Sequential permuted MNIST · Permuted MNIST | performance on previously learned tasks | Improved |
| Use full experience replay with stored past-task data instead of ECLA | Sequential permuted MNIST · Permuted MNIST | performance on previously learned tasks | Improved |
| Use ECLA rather than full experience replay | Sequential permuted MNIST · Permuted MNIST | cross-domain concept alignment | Improved |
| Learn a second digit-recognition domain with ECLA and 10 labeled examples per class | ECLA · MNIST → USPS and USPS → MNIST | performance on the first task after learning the second | Improved |
| Transfer from the first digit-recognition domain using ECLA | ECLA · MNIST → USPS and USPS → MNIST | initial performance on the second task | Improved |
| Use ECLA on visually similar domains rather than unrelated domains | ECLA · Digit recognition versus permuted MNIST | task-agnostic concept formation | Mixed |
Closest papers by meaning
- Generative vs. Discriminative: Rethinking The Meta-Continual Learning (NeurIPS 2021 · similarity 0.91)
- Recall-Oriented Continual Learning with Generative Adversarial Meta-Model (AAAI 2024 · similarity 0.89)
- A Unified and General Framework for Continual Learning (ICLR 2024 · similarity 0.88)
- Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning (NeurIPS 2025 · similarity 0.88)
- Task-Free Continual Generation and Representation Learning via Dynamic Expansionable Memory Cluster (AAAI 2024 · similarity 0.87)
- Language Guided Concept Bottleneck Models for Interpretable Continual Learning (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
