Research map / Label-efficient and robust learning / Noisy labels
Unsupervised Learning from Noisy Networks with Applications to Hi-C Data
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 |
|---|---|---|---|
| Denoising the highest-resolution Hi-C map with OPT1 (single network) before clustering (ablation) | Louvain clustering on Hi-C · GM12878 chr14 and chr21 simulated Hi-C | cluster agreement with ground truth (qualitative) | Helped |
| Pooling multiple Hi-C resolutions with learned weights (OPT2) (ablation) | Denoised Hi-C network · GM12878 chr14 and chr21 simulated Hi-C | cluster size / agreement with ground truth (qualitative) | Helped |
| Adding Capture-C high-confidence links (OPT6) to multi-resolution denoising (ablation) | Multi-resolution denoised Hi-C network · GM12878 chr14 and chr21 simulated Hi-C | cluster agreement with ground truth (qualitative) | Helped |
| Increasing distance-dependent random noise on the network | Louvain baseline on highest-resolution Hi-C · Simulated Hi-C noise sweep | NMI | Hurt |
| Increasing noise on the network, compared with the proposed multi-resolution denoiser | Proposed denoising framework · Simulated Hi-C noise sweep | NMI | Mixed |
| Ratio of histone-mark covariation within vs between domains and CTCF boundary binding, proposed vs baseline | Proposed denoising framework · GM12878 Hi-C domains | histone covariation ratio and CTCF binding fraction | Helped |
Closest papers by meaning
- Geometric Generative Modeling with Noise-Conditioned Graph Networks (ICML 2025 · similarity 0.85)
- The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks (NeurIPS 2024 · similarity 0.84)
- Local Graph Clustering with Noisy Labels (ICLR 2024 · similarity 0.84)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.84)
- Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis (AAAI 2024 · similarity 0.83)
- Community Detection Guarantees using Embeddings Learned by Node2Vec (NeurIPS 2024 · similarity 0.83)
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.