Research map / Probabilistic and scientific modeling / Variational and generative sampling
Multi-Entity Dependence Learning With Rich Context via Conditional Variational Auto-Encoder
Luming Tang, Yexiang Xue, Di Chen, Carla Gomes
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 MEDL_CVAE rather than independent prediction with the same feature inputs | eBird models · eBird test | Neg. JLL: 33.73 -> 28.24 | Improved |
| Use MEDL_CVAE rather than PCC with the same feature inputs | eBird models · eBird test | Neg. JLL: 34.48 -> 28.24 | Improved |
| Use MEDL_CVAE rather than DMSE with NLCD features | eBird models · eBird test | Neg. JLL: 30.53 -> 30.86 | Improved |
| Add satellite image input to the NLCD+MLP+MEDL_CVAE model (ablation) | MEDL_CVAE · eBird test | Neg. JLL: 30.86 -> 28.24 | Improved |
| Use Hist128 instead of Hist64 image summaries (ablation) | MEDL_CVAE · eBird test | Neg. JLL: 28.86 -> 28.71 | Improved |
| Use Image64 input instead of Hist128 input (ablation) | MEDL_CVAE · eBird test | Neg. JLL: 28.71 -> 28.24 | Improved |
| Use MEDL_CVAE rather than independent prediction with Image64+MLP | Amazon models · Amazon | Neg. JLL: 2.83 -> 2.37 | Improved |
| Use MEDL_CVAE rather than PCC with Image64+MLP | Amazon models · Amazon | Neg. JLL: 2.95 -> 2.37 | Improved |
| Use Hist128+MLP instead of Image64+MLP as MEDL_CVAE input (ablation) | MEDL_CVAE · Amazon | Neg. JLL: 2.37 -> 2.09 | Improved |
| Use CNN instead of MLP with Image64 input (ablation) | MEDL_CVAE · Amazon | Neg. JLL: 2.37 -> 2.03 | Improved |
| Add satellite images to the NLCD-only independent eBird model (ablation) | Independent MLP · eBird test | Neg. JLL: 36.32 -> 33.73 | Improved |
Closest papers by meaning
- TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing (NeurIPS 2024 · similarity 0.84)
- Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders (ICML 2025 · similarity 0.82)
- Environment-Robust Representation Learning with Empirical Bayes (NeurIPS 2026 · similarity 0.82)
- A Theory for Conditional Generative Modeling on Multiple Data Sources (ICML 2025 · similarity 0.82)
- SoftCVI: Contrastive variational inference with self-generated soft labels (ICLR 2025 · similarity 0.82)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.82)
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.
