Research map / Probabilistic and scientific modeling / Causal discovery
Diverse Dictionary Learning
Yujia Zheng, Zijian Li, Shunxing Fan, Andrew Gordon Wilson, Kun Zhang
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 dependency (Jacobian) sparsity to FactorVAE | FactorVAE · Shapes3D | DCI: 0.484 -> 0.575 | Improved |
| add dependency sparsity to FactorVAE | FactorVAE · MPI3D | FactorVAE score: 0.599 -> 0.639 | Improved |
| add dependency sparsity to EncDiff | EncDiff · Shapes3D | DCI: 0.901 -> 0.947 | Improved |
| add dependency sparsity to EncDiff | EncDiff · Cars3D | FactorVAE score: 0.779 -> 0.756 | Hurt |
| add dependency sparsity to DisCo | DisCo · Cars3D | FactorVAE score: 0.727 -> 0.789 | Improved |
| add dependency sparsity to DisCo | DisCo · Shapes3D | DCI: 0.710 -> 0.712 | No clear effect |
| add latent sparsity (L1 on Z) to FactorVAE (ablation) | FactorVAE · Cars3D | FactorVAE score: 0.708 -> 0.501 | Hurt |
| add latent sparsity to FactorVAE (ablation) | FactorVAE · MPI3D | FactorVAE score: 0.599 -> 0.440 | Hurt |
| add latent sparsity to EncDiff (ablation) | EncDiff · Shapes3D | FactorVAE score: 0.9999 -> 0.967 | Hurt |
| add latent sparsity to DisCo (ablation) | DisCo · MPI3D | FactorVAE score: 0.396 -> 0.308 | Hurt |
| replace latent sparsity with dependency sparsity (ablation) | generative disentanglement models · Shapes3D/Cars3D/MPI3D | FactorVAE score / DCI | Improved |
| data satisfying Sufficient Diversity vs fully dense dependencies (ablation) | VAE with dependency sparsity · synthetic | MCC | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FactorVAE — FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns (AAAI 2022) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Nonparametric Identification of Latent Concepts (ICML 2025 · similarity 0.86)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.86)
- When does LeJEPA learn a World Model? (NeurIPS 2026 · similarity 0.85)
- Identifiability Guarantees for Causal Disentanglement from Purely Observational Data (NeurIPS 2024 · similarity 0.85)
- Identifiable Latent Polynomial Causal Models through the Lens of Change (ICLR 2024 · similarity 0.84)
- Mapping the Multiverse of Latent Representations (ICML 2024 · similarity 0.84)
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.
