Research map / Probabilistic and scientific modeling / Variational and generative sampling
Deep Dynamic Poisson Factorization Model
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 |
|---|---|---|---|
| Use DDPFA (neural-network implicit priors, deep latent layers) instead of PGDS, LSTM, PFA | DDPFA vs baselines · Synthetic SDS1-SDS4 and real datasets | MSE / PMSE | Mixed |
| Ladder-like architecture (layers combine independent variables with upper-layer latents) instead of plain stacked layers (ablation) | DDPFA 10-10-10 · ICEWS / NIPS / EBOLA | MSE: ICEWS 2.94->2.88; NIPS 51.24->49.81; EBOLA 382.17->379.08 | Helped |
| Expand bottom layer dimension versus upper layers / add layers (ablation) | DDPFA · ICEWS / NIPS / EBOLA | MSE: e.g. 10-10 vs 10-10-10 nearly identical; 32-32-32 vs 10-10-10 small change | No clear effect |
| Increase layer sizes to 32-32-32 with ladder structure (ablation) | DDPFA · NIPS | MSE: 51.14 -> 49.26 (ladder 32-32-32) | Helped |
Closest papers by meaning
- Fully Heteroscedastic Count Regression with Deep Double Poisson Networks (ICML 2025 · similarity 0.84)
- Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric Factorization (ICML 2024 · similarity 0.82)
- Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference (ICML 2025 · similarity 0.82)
- Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting (ICML 2024 · similarity 0.82)
- Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries (ICLR 2025 · similarity 0.81)
- Latent variable model for high-dimensional point process with structured missingness (ICML 2024 · similarity 0.81)
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.