Research map / Continual learning / Online and replay-based
Continual Variational Autoencoder via Continual Generative Knowledge Distillation
Fei Ye, Adrian G. Bors
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 CGKD-GAN instead of the strongest baseline LTS | Lifelong generative modelling · MSFIRC | FID: 67.7 -> 49.0 | Improved |
| Use CGKD-GAN instead of the strongest baseline CN-DPM | Lifelong generative modelling · CelebA-Chair | FID: 15.82 -> 14.68 | Improved |
| Use GAN experts rather than VAE experts in CGKD | CGKD · MSFIRC | FID: 102.6 -> 49.0 | Improved |
| Use GAN experts rather than VAE experts in CGKD | CGKD · CelebA-Chair | FID: 16.21 -> 14.68 | Improved |
| Add expert pruning (ablation) | CGKD-GAN · MSFIRC | FID: 49.0 -> 43.1 | Mixed |
| Add expert pruning (ablation) | CGKD-VAE · MSFIRC | FID: 102.6 -> 100.0 | Improved |
| Vary the KIAM expansion threshold ν (ablation) | CGKD-GAN · MSFIRC | FID | No clear effect |
Closest papers by meaning
- Task-Free Continual Generation and Representation Learning via Dynamic Expansionable Memory Cluster (AAAI 2024 · similarity 0.90)
- Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning (NeurIPS 2025 · similarity 0.88)
- Dynamic Expansion Diffusion Learning for Lifelong Generative Modelling (AAAI 2025 · similarity 0.87)
- Learn more, but bother less: parameter efficient continual learning (NeurIPS 2024 · similarity 0.87)
- Recall-Oriented Continual Learning with Generative Adversarial Meta-Model (AAAI 2024 · similarity 0.87)
- Self-Expansion of Pre-trained Models with Mixture of Adapters for 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.
