Research map / Federated learning and privacy / Privacy attacks and secure learning
Inferring Networks From Random Walk-Based Node Similarities
Jeremy Hoskins, Cameron Musco, Christopher Musco, Babis Tsourakakis
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 |
|---|---|---|---|
| Increase the sampled resistance fraction from 10% to 25% | Gradient descent graph learning · Grid, σ²=0 | % edges learned: 20.54 -> 88.39 | Improved |
| Add Gaussian noise with σ²=.1 to the resistance measurements | Gradient descent graph learning · Grid, f=10% | % edges learned: 20.54 -> 25.89 | Improved |
| Increase the sampled resistance fraction from 10% to 25% | Gradient descent graph learning · k-nn, σ²=0 | % edges learned: 44.54 -> 72.68 | Improved |
| Increase the sampled resistance fraction from 10% to 25% | Gradient descent graph learning · FB Small C, σ²=0 | % edges learned: $57.03 -> $59.51 | Improved |
| Use the convex minimum-total-edge-weight formulation instead of least squares | Graph reconstruction · Grid, f=25%, σ²=0 | % edges learned: 88.39 -> 25.00 | Hurt |
| Increase the sampled resistance fraction from 10% to 25% | Gradient descent graph learning · FB Large B, σ²=.1 | effective resistance generalization error: $.14532 -> $.36095 | Hurt |
| Add Gaussian noise with σ²=.1 to the resistance measurements | Gradient descent graph learning · FB Small A, f=10% | % edges learned: $44.54 -> $53.64 | Improved |
Closest papers by meaning
- Community Detection Using Restrained Random-walk Similarity (TPAMI 2019 · similarity 0.86)
- Differentially Private Graph Diffusion with Applications in Personalized PageRanks (NeurIPS 2024 · similarity 0.84)
- Differentially Private Decentralized Learning with Random Walks (ICML 2024 · similarity 0.83)
- On provable privacy vulnerabilities of graph representations (NeurIPS 2024 · similarity 0.83)
- Revisiting Random Walks for Learning on Graphs (ICLR 2025 · similarity 0.82)
- Node Similarities under Random Projections: Limits and Pathological Cases (ICLR 2025 · similarity 0.82)
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.
