AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

SFCLTA: Spectral Fusion Contrastive Learning with Topology-Adaptive Graph Augmentation

Zhuo Xu, Lu Bai, Jincheng Li, Lixin Cui, Ming Li, Hangyuan Du, Yue Wang

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Graph contrastive learning analysis

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
add high-pass filter branch (ablation)SFCLTA · Amazon-Photo and PPIaccuracyImproved
add low-pass filter branch (ablation)SFCLTA · Amazon-Photo and PPIaccuracyImproved
add feature reconstruction pretext task (ablation)SFCLTA · Amazon-Photo and PPIaccuracyImproved
use topology-adaptive augmentation instead of random edge rewiring (ablation)SFCLTA · Amazon-Photo and PPIaccuracyImproved
increase augmentation ratio above 0.2 (ablation)SFCLTA · Amazon-Photoaccuracy: stable (over 85%) for 0.05-0.15; rda=0.1 best; drops beyond 0.2Hurt
add Gaussian noise (std up to 2) to high-pass features (ablation)SFCLTA · Amazon-PhotoaccuracyNo 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