Research map / Continual learning / Online and replay-based
Wasserstein Expansible Variational Autoencoder for Discriminative and Generative Continual Learning
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 |
|---|---|---|---|
| add energy-based sample selection (ablation) | WEVAE · Split MNIST (density estimation) | log-likelihood: -99.29 -> -89.66 | Improved |
| add energy-based sample selection (ablation) | WEVAE · Split CIFAR10 (classification) | accuracy (%): 51.38 -> 55.23 | Improved |
| add energy-based sample selection (ablation) | WEVAE · Split CIFAR100 (classification) | accuracy (%): 23.18 -> 25.07 | Improved |
| add energy-based sample selection (ablation) | WEVAE · M-C (MNIST+CIFAR10 stream) | accuracy (%): 56.98 -> 59.07 | Improved |
| use Wasserstein-based expansion instead of prior dynamic expansion (without sample selection) | WEVAE-NoS vs Dynamic-OCM · Split CIFAR10 (classification) | accuracy (%): 49.16 -> 51.38 | Improved |
| lower the expansion threshold lambda (more components) (ablation) | WEVAE · Split MNIST (density estimation) | negative log-likelihood | No clear effect |
| vary memory buffer size (ablation) | WEVAE vs baselines · Cross-Domain | negative log-likelihood | Improved |
| change batch size (ablation) | WEVAE · Split MNIST | negative log-likelihood | No clear effect |
Closest papers by meaning
- BooVAE: Boosting Approach for Continual Learning of VAE (NeurIPS 2021 · similarity 0.91)
- Learning Dynamic Latent Spaces for Lifelong Generative Modelling (AAAI 2023 · similarity 0.90)
- Continual Unsupervised Generative Modeling (TPAMI 2025 · similarity 0.89)
- Continual Variational Autoencoder Learning via Online Cooperative Memorization (ECCV 2022 · similarity 0.89)
- Continual Variational Autoencoder via Continual Generative Knowledge Distillation (AAAI 2023 · similarity 0.89)
- BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning (CVPR 2025 · similarity 0.86)
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.
