Research map / Label-efficient and robust learning / Recognition and long-tail
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 group-Lasso sparsity penalty to task-specific multiclass SVM predictors (ablation) | metric-based meta-learning on mini-ImageNet · mini-ImageNet meta-validation | meta-validation accuracy | No clear effect |
| increase sparsity level of task-specific predictor beyond ~30% (ablation) | sparse meta-learning on mini-ImageNet · mini-ImageNet meta-validation | meta-validation accuracy | Hurt |
| L1 (Lasso) penalty on linear regression over disentangled representation vs entangled, small sample regime (ablation) | simulated linear regression on frozen representation · simulation, l/m = 5% | test generalization | Helped |
| inner Lasso regularization of task predictors (bi-level) for disentanglement | 3D Shapes multi-task regression · 3D Shapes disentanglement | MCC | Helped |
| use correlated latents with inner-Ridge + linear ICA instead of inner-Lasso (ablation) | 3D Shapes disentanglement · 3D Shapes with correlated latents | MCC | Hurt |
| add noise on latent variables (ablation) | inner-Ridge with ICA vs inner-Lasso · 3D Shapes | MCC | Hurt |
Closest papers by meaning
- Leveraging sparse and shared feature activations for disentangled representation learning (NeurIPS 2023 · similarity 0.91)
- DiSparse: Disentangled Sparsification for Multitask Model Compression (CVPR 2022 · similarity 0.89)
- Disentangling Representations through Multi-task Learning (ICLR 2025 · similarity 0.88)
- Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning (ICLR 2025 · similarity 0.88)
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (ICML 2019 · similarity 0.88)
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity (ICLR 2024 · 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.