Research map / Probabilistic and scientific modeling / Molecules and proteins
Multiparameter Persistence Image for Topological Machine Learning
Mathieu Carrière, Andrew Blumberg
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 multiparameter persistence image instead of 1D persistence image | Persistence features · Immunofluorescence survival | accuracy: 71.1 -> 79.1 | Improved |
| use MP-I instead of nearest-neighbor distribution features | XGBoost · Immunofluorescence survival | accuracy: 67.2 -> 79.1 | Improved |
| use MP-I instead of MP-K | multiparameter descriptors · Immunofluorescence survival | accuracy: 77.6 -> 79.1 | Improved |
| use MP-I instead of MP-L | multiparameter descriptors · UCR time series | accuracy: 64.6 -> 83.8 on SwedishLeaf | Improved |
| use MP-I instead of MP-K | multiparameter descriptors · UCR time series computation time dim 0 | computation time (s): 147668.1 -> 599.5 on MedicalImages | Improved |
| use MP-I instead of 1D P-I | persistence image · UCR SwedishLeaf | accuracy: 37.1 -> 83.8 | Improved |
| MP-I vs DTW baselines | MP-I · UCR SyntheticControl | accuracy: 99.3 -> 60.0 | Hurt |
| use MP-I instead of MP-L | multiparameter descriptors · UCR GunPoint | accuracy: 94.0 -> 90.7 | Hurt |
| use MP-I for graph classification vs other multiparameter summaries | multiparameter descriptors · graph classification | accuracy | No clear effect |
| small noise in slice endpoints (ablation) | MP-I · ECG200 | accuracy | Mixed |
Closest papers by meaning
- Multiparameter Persistence Landscapes (JMLR 2020 · similarity 0.86)
- Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor (JMLR 2018 · similarity 0.84)
- A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions (NeurIPS 2023 · similarity 0.84)
- Topo-Geometric Analysis of Variability in Point Clouds Using Persistence Landscapes (TPAMI 2024 · similarity 0.83)
- Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence (AAAI 2024 · similarity 0.81)
- Towards Scalable Topological Regularizers (ICLR 2025 · similarity 0.80)
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.
