Research map / Learning theory and algorithms / Clustering
Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm
Kejun Huang, Xiao Fu, Nikolaos D. Sidiropoulos
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 AnchorFree instead of FastAnchor | topic mining · TDT2, F=5 | ClustAcc: 0.63 -> 0.92 | Improved |
| use AnchorFree instead of FastAnchor | topic mining · TDT2, F=5 | Coh: -641.79 -> -405.19 | Improved |
| use AnchorFree instead of FastAnchor | topic mining · TDT2, F=5 | SimCount: 13.06 -> 4.40 | Improved |
| use AnchorFree instead of XRAY | topic mining · TDT2, F=25 | SimCount: 101.52 -> 133.42 | Hurt |
| use AnchorFree instead of XRAY | topic mining · Reuters-21578, F=5 | Coh: -581.73 -> -762.64 | Hurt |
| use AnchorFree instead of XRAY | topic mining · Reuters-21578, F=10 | SimCount: 130.82 -> 86.02 | Improved |
| use AnchorFree instead of XRAY | topic mining · Reuters-21578, F=3 | SimCount: 3.86 -> 7.36 | Hurt |
| use AnchorFree instead of XRAY | topic mining · Reuters-21578, F=25 | ClustAcc: 0.37 -> 0.47 | Improved |
| increase number of topics F from 3 to 25 | AnchorFree · TDT2 | ClustAcc: 0.98 -> 0.74 | Hurt |
| increase number of topics F from 3 to 25 | AnchorFree · Reuters-21578 | ClustAcc: 0.79 -> 0.47 | Hurt |
| use AnchorFree instead of XRAY on synthetic data without anchor words | topic matrix recovery · Synthetic F=5 | C estimation error: 0.0800 -> 5.83e-20 | Improved |
| use AnchorFree instead of XRAY on synthetic data | correlation matrix recovery · Synthetic F=30 | E estimation error: 67.54 -> 5.80e-12 | Improved |
Closest papers by meaning
- Anchor-Free Correlated Topic Modeling (TPAMI 2018 · similarity 0.96)
- Sparse Topic Modeling via Spectral Decomposition and Thresholding (JMLR 2026 · similarity 0.86)
- Optimal Estimation of Sparse Topic Models (JMLR 2020 · similarity 0.85)
- Probabilistic Non-Negative Matrix Factorization and Its Robust Extensions for Topic Modeling (AAAI 2017 · similarity 0.84)
- Algorithms for Generalized Topic Modeling (AAAI 2018 · similarity 0.84)
- On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling (AAAI 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.
