Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Nonlinear Feature Selection from High-Dimensional Signed Networks
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 |
|---|---|---|---|
| use block HSIC estimator with nonlinear kernel Lasso instead of matrix-factorization linear methods | SignedLasso vs SignedFS · Epinions | run time (s): 7428 -> 1837 | Helped |
| use block HSIC estimator instead of matrix-factorization methods | SignedLasso vs SignedFS · Wiki-RfA | run time (s): 16860 -> 636 | Helped |
| use block HSIC estimator instead of matrix-factorization methods | SignedLasso vs SignedFS · Epinions | peak memory (MiB): 3249 -> 6487 | Hurt |
| use nonlinear feature selection with signed-network embedding instead of linear SignedFS | feature selection · Epinions, Wiki-RfA | ACC/NMI/F1 | Helped |
| add negative links (signed) rather than positive only | network feature selection · Epinions, Wiki-RfA | ACC/NMI/F1 | Helped |
| vary block size B (20-50) and embedding dimension c (10-40) (ablation) | SignedLasso · Epinions, Wiki-RfA | ACC, NMI | No clear effect |
Closest papers by meaning
- Unsupervised Feature Selection on Networks: A Generative View (AAAI 2016 · similarity 0.88)
- FILE: A Novel Framework for Predicting Social Status in Signed Networks (AAAI 2018 · similarity 0.84)
- SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction (NeurIPS 2025 · similarity 0.84)
- DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks (NeurIPS 2024 · similarity 0.82)
- Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection (NeurIPS 2025 · similarity 0.81)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.81)
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.