Research map / Probabilistic and scientific modeling / Dynamical systems
Neural Ideal Point Estimation Network
Kyungwoo Song, Wonsung Lee, Il-Chul Moon
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 NIPEN-PGM with VAE bill-text representations and integrated voting/network factors instead of CDL | NIPEN-PGM (VAE) · Politic2013 | RMSE: $0.1834^{\dagger}$ ($\pm$0.0008) -> \textbf{0.1753**} ($\pm$0.0007) | Improved |
| Use NIPEN-PGM with VAE bill-text representations and integrated voting/network factors instead of CDL | NIPEN-PGM (VAE) · Politic2016 | RMSE: $0.1780^{\dagger}$ ($\pm$0.0013) -> 0.1753** ($\pm$0.0017) | Improved |
| Use NIPEN-Tensor instead of the strongest baseline | NIPEN-Tensor · Politic2016 | NALL: $0.1106^{\dagger}$ ($\pm$0.0017) -> \textbf{0.1057**} ($\pm$0.0022) | Improved |
| Use VAE instead of SDAE for bill-text representations (ablation) | NIPEN-PGM · Politic2013 | RMSE: 0.1801** ($\pm$0.0014) -> \textbf{0.1753**} ($\pm$0.0007) | Improved |
| Use VAE instead of SDAE for bill-text representations (ablation) | NIPEN-PGM · Politic2016 | MAE: 0.0560** ($\pm$0.0004) -> 0.0570** ($\pm$0.0012) | Hurt |
| Use the full influence matrix instead of its low-rank approximation (ablation) | NIPEN-PGM (VAE) · Politic2013 | RMSE: 0.1804 ($\pm$0.0089) -> \textbf{0.1753**} ($\pm$0.0007) | Improved |
| Use the full influence matrix instead of its low-rank approximation (ablation) | NIPEN-PGM (VAE) · Politic2016 | Accuracy: 0.9571 ($\pm$0.0039) -> 0.9590** ($\pm$0.0010) | Improved |
| Use NIPEN-Tensor, which models cross-topic interactions, rather than NIPEN-PGM(VAE) (ablation) | NIPEN models · Politic2016 | RMSE: 0.1753** ($\pm$0.0017) -> \textbf{0.1729**} ($\pm$0.0015) | Improved |
| Use NIPEN-Tensor rather than NIPEN-PGM(VAE) (ablation) | NIPEN models · Politic2013 | RMSE: \textbf{0.1753**} ($\pm$0.0007) -> 0.1818** ($\pm$0.0008) | Hurt |
Closest papers by meaning
- Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models (AAAI 2025 · similarity 0.83)
- C-Voting: Confidence-Based Test-Time Voting without Explicit Energy Functions (ICLR 2026 · similarity 0.80)
- How many classifiers do we need? (NeurIPS 2024 · similarity 0.79)
- Linear Representations of Political Perspective Emerge in Large Language Models (ICLR 2025 · similarity 0.79)
- Learning to Manipulate Under Limited Information (AAAI 2025 · similarity 0.79)
- Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data (NeurIPS 2024 · similarity 0.79)
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.
