Research map / Learning theory and algorithms / Clustering
Lifelong Spectral Clustering
Gan Sun, Yang Cong, Qianqian Wang, Jun Li, Yun Fu
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 L²SC's lifelong shared libraries instead of MTCMRL | spectral clustering · WebKB4 | Avg.NMI (%): 40.58±3.04 -> 46.26±1.84 | Improved |
| Use L²SC's lifelong shared libraries instead of MTCMRL | spectral clustering · Reuters | Avg.NMI (%): 85.96±0.82 -> 87.71±0.47 | Improved |
| Use L²SC's lifelong shared libraries instead of MTCMRL | spectral clustering · 20NewsGroups | Avg.NMI (%): 48.39±0.98 -> 52.84±0.68 | Improved |
| Use L²SC instead of MTCMRL | spectral clustering · WebKB4 | runtime (seconds): 14.51±1.30 -> 2.69±0.02 | Improved |
| Use L²SC instead of MTCMRL | spectral clustering · Reuters | runtime (seconds): 8.26±0.28 -> 1.32±0.01 | Improved |
| Use L²SC instead of MTCMRL | spectral clustering · 20NewsGroups | runtime (seconds): 384.52±19.55 -> 9.95±0.29 | Improved |
| Increase the number of learned tasks and transfer accumulated knowledge | L²SC · WebKB4 | Purity and NMI | Improved |
| Set the cluster count to 4 despite Task1 having 3 clusters | L²SC · 20NewsGroups Task1 | Purity: 81.59±1.45 vs 81.05±1.05 | Hurt |
| Tune λ and μ to an appropriate ratio | L²SC · WebKB4 | clustering performance | Improved |
Closest papers by meaning
- What and How: Generalized Lifelong Spectral Clustering via Dual Memory (TPAMI 2021 · similarity 0.93)
- A Novel and Effective Method to Directly Solve Spectral Clustering (TPAMI 2024 · similarity 0.90)
- Discrete and Balanced Spectral Clustering With Scalability (TPAMI 2023 · similarity 0.89)
- Unified Spectral Clustering With Optimal Graph (AAAI 2018 · similarity 0.88)
- SpectralNet: Spectral Clustering using Deep Neural Networks (ICLR 2018 · similarity 0.88)
- Pass-Efficient Algorithms for Graph Spectral Clustering (Student Abstract) (AAAI 2024 · similarity 0.84)
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.
