Research map / Graph learning / Graph algorithms and clustering
ARTree: A Deep Autoregressive Model for Phylogenetic Inference
Tianyu Xie, Cheng 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 |
|---|---|---|---|
| replace SBN-EM-alpha with ARTree for topology density estimation | SBN · DS1 TDE | KL divergence: 0.0130 -> 0.0045 | Improved |
| replace SBN-EM-alpha with ARTree for topology density estimation | SBN · DS5 TDE | KL divergence: 0.8218 -> 0.6266 | Improved |
| replace SBN-SGA with ARTree (same uniform init, gradient training) | SBN-SGA · DS1 TDE | KL divergence: 0.0504 -> 0.0045 | Improved |
| use gradient-based SBN-SGA instead of SBN-EM | SBN · DS2-8 TDE | KL divergence: 0.0199 -> 0.0118 | Mixed |
| increase training sample size M | ARTree vs SBNs · DS1 TDE | KL divergence | Improved |
| replace SBN with ARTree as tree topology variational distribution in VBPI | VBPI · DS1 | KL divergence: 0.0707 -> 0.0097 | Improved |
| replace SBN with ARTree as tree topology variational distribution in VBPI | VBPI · DS5 | KL divergence: 1.2472 -> 0.8979 | Improved |
| replace SBN with ARTree in VBPI | VBPI · DS1 | ELBO: -7110.24 -> -7110.09 | No clear effect |
| replace SBN with ARTree in VBPI | VBPI · DS6 | ELBO: -6728.65 -> -6728.65 | No clear effect |
| remove time guidance (b_n=0) from ARTree readout (ablation) | ARTree · DS1 VBPI | ELBO | Hurt |
| use fewer particles (K=5) in training objective | ARTree · DS1 VBPI | ELBO | Improved |
| randomize taxa order across 50 random orders (ablation) | ARTree · DS1 VBPI | KL divergence | No clear effect |
Closest papers by meaning
- PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders (ICLR 2025 · similarity 0.91)
- PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation (NeurIPS 2024 · similarity 0.90)
- Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes (NeurIPS 2026 · similarity 0.90)
- PhyloGFN: Phylogenetic inference with generative flow networks (ICLR 2024 · similarity 0.89)
- Likelihood-free inference of phylogenetic tree posterior distributions (NeurIPS 2026 · similarity 0.87)
- Variational Phylogenetic Inference with Products over Bipartitions (ICML 2025 · 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.
