Research map / Learning theory and algorithms / Clustering
Viral Clustering: A Robust Method to Extract Structures in Heterogeneous Datasets
Vahan Petrosyan, Alexandre Proutiere
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 VC instead of BIC for estimating number of clusters | Viral Clustering · Artificial Mixture (20 clusters) | correct k* predictions out of 50: 7 -> 32 | Improved |
| use VC instead of BIC on exponential clusters | Viral Clustering · Artificial Exp (20 clusters) | correct k* predictions out of 50: 0 -> 50 | Improved |
| use VC instead of BIC on Beta clusters | Viral Clustering · Artificial Beta (20 clusters) | correct k* predictions out of 50: 15 -> 33 | Improved |
| use VC instead of BIC on Jump5 (exponential clusters) | Viral Clustering · Jump5 | correct k* predictions out of 50: 11 -> 48 | Improved |
| use VC instead of BIC on well-separated Gaussian-like Gap datasets | Viral Clustering · Gap2 (k*=3) | correct k* predictions out of 50: 50 -> 48 | No clear effect |
| use VC instead of Jump on Gap1 and Gap5 | Viral Clustering · Gap1/Gap5 | correct k* predictions out of 50: 0 -> 50 | Improved |
| use VC instead of Jump with prediction range one to ten | Viral Clustering · Artificial Exp/T/Beta/Mixture/Gaussian | mean predicted k (true 20): 26.4 -> 20 | Improved |
| use VC instead of Silhouette index on Exp clusters | Viral Clustering · Artificial Exp (20 clusters) | correct k* predictions out of 50: 3 -> 50 | Improved |
| use VC instead of CH index on Jump1 | Viral Clustering · Jump1 (k*=5) | correct k* predictions out of 50: 46 -> 39 | Hurt |
| use VC instead of BIC on Jump1 | Viral Clustering · Jump1 (k*=5) | correct k* predictions out of 50: 48 -> 39 | Hurt |
| use VC instead of Jump on Jump2 | Viral Clustering · Jump2 (k*=5, p=10) | correct k* predictions out of 50: 42 -> 47 | Improved |
| use VC instead of other indices on Furie dataset | Viral Clustering · Furie (k*=10) | predicted number of clusters: 11 | No clear effect |
Closest papers by meaning
- Statistical Inference for Cluster Trees (NeurIPS 2016 · similarity 0.85)
- Compact Representation of Uncertainty in Clustering (NeurIPS 2018 · similarity 0.84)
- BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits (NeurIPS 2020 · similarity 0.84)
- Clustering Small Samples With Quality Guarantees: Adaptivity With One2all PPS (AAAI 2018 · similarity 0.83)
- Dynamic Clustering Algorithms via Small-Variance Analysis of Markov Chain Mixture Models (TPAMI 2018 · similarity 0.83)
- A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random (NeurIPS 2025 · 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.
