Research map / Probabilistic and scientific modeling / Molecules and proteins
HDTree: Generative Modeling of Cellular Hierarchies for Robust Lineage Inference
Zelin Zang, WenZhe Li, Yongjie Xu, Chang Yu, Changxi Chi, Jingbo Zhou, Zhen Lei, Stan Z. Li
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 hierarchical tree codebook (ablation) | HDTree · MNIST | dendrogram purity: 87.4 -> 92.7 | Improved |
| add soft contrastive loss (ablation) | HDTree · MNIST | dendrogram purity: 78.9 -> 92.7 | Improved |
| add hierarchical quantization loss (ablation) | HDTree · MNIST | dendrogram purity: 84.1 -> 92.7 | Improved |
| add hierarchical tree codebook (ablation) | HDTree · ECL | dendrogram purity: 58.7 -> 69.0 | Improved |
| add soft contrastive loss (ablation) | HDTree · ECL | dendrogram purity: 55.6 -> 69.0 | Improved |
| add hierarchical quantization loss (ablation) | HDTree · ECL | dendrogram purity: 61.4 -> 69.0 | Improved |
| add hierarchical tree codebook (ablation) | HDTree · MNIST | clustering accuracy: 84.1 -> 96.6 | Improved |
| add soft contrastive loss (ablation) | HDTree · ECL | clustering accuracy: 68.3 -> 83.2 | Improved |
| replace TreeVAE with HDTree (unified codebook plus diffusion decoder) | TreeVAE · MNIST | dendrogram purity: 87.9 -> 91.9 | Improved |
| replace TreeVAE with HDTree | TreeVAE · CIFAR-10 | clustering accuracy: 52.9 -> 73.2 | Improved |
| use HDTree instead of TreeVAE | TreeVAE · Weinreb | average: 49.5 -> 59.3 | Improved |
| use HDTree instead of TreeVAE on C. elegans 500-750 | TreeVAE · C. elegans time-point ratio | neighborhood ratio: 62.8% -> 66.3% | Improved |
Closest papers by meaning
- Reconstructing Cell Lineage Trees from Phenotypic Features with Metric Learning (ICML 2025 · similarity 0.91)
- Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes (NeurIPS 2026 · similarity 0.84)
- KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference (NeurIPS 2025 · similarity 0.82)
- What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits (ICLR 2025 · similarity 0.82)
- TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics (NeurIPS 2026 · similarity 0.82)
- STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations (NeurIPS 2026 · 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.
