AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Federated Spectral Clustering via Secure Similarity Reconstruction

Dong Qiao, Chris Ding, Jicong Fan

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Private federated aggregation · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use FedSC (federated) instead of DSCFedSC · COIL20clustering accuracy: 0.1009 ± 0.0100 -> 0.7828 ± 0.0231Improved
Use FedSC instead of vanilla SC on BankFedSC · Bankclustering accuracy: 0.5918 ± 0.0000 -> 0.7672 ± 0.1457Improved
Use FedSC instead of vanilla SC on COIL20FedSC · COIL20clustering accuracy: 0.8025 ± 0.0009 -> 0.7828 ± 0.0231No clear effect
Use FedSC instead of vanilla SC on ORLFedSC · ORLclustering accuracy: 0.7865 ± 0.0106 -> 0.7235 ± 0.0170Hurt
Use FedSC instead of Kmeans on COIL20FedSC · COIL20clustering accuracy: 0.6113 ± 0.0534 -> 0.7828 ± 0.0231Improved
Use FedSC instead of vanilla SC on USPS under noise 0.3 sigmaFedSC · USPSclustering accuracy: 0.6720 ± 0.0044 -> 0.6884 ± 0.0509Improved
Increase Gaussian noise from raw to 0.7 sigma on Iris (ablation)FedSC · Irisclustering accuracy: 0.9000 ± 0.0031 -> 0.6120 ± 0.0455Hurt
Split data across 8 clients instead of 1 (ablation)FedSC · ORLclustering accuracy: 0.7937 ± 0.0084 -> 0.7112 ± 0.0258Hurt
Split data across 8 clients instead of 1 (ablation)FedSC · Irisclustering accuracy: 0.9007 ± 0.0086 -> 0.8993 ± 0.0165No clear effect
Split data across 8 clients instead of 1 (ablation)FedSC · Bankclustering accuracy: 0.7536 ± 0.1271 -> 0.6821 ± 0.1405Hurt
Perturb factors C and Z (alpha_c 0 -> 0.15, alpha_z=0) (ablation)FedSC · COIL20clustering accuracy: 0.7831±0.0268 -> 0.4835±0.0526Hurt
Perturb factor Z (alpha_z 0 -> 0.15, alpha_c=0) (ablation)FedSC · COIL20clustering accuracy: 0.7831±0.0268 -> 0.7881±0.0223No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy