AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Multi-view adaptive graph convolutions for graph classification

Nikolas Adaloglou, Nicholas Vretos, Petros Daras

ECCV 2020 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 12 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
increase views per layer from 2 to 6 (ablation)MV-AGC · ENZYMESaccuracy: 56.02 ± 6.3 -> 62.27 ± 4.3Improved
increase views per layer from 2 to 9 (ablation)MV-AGC · MUTAGaccuracy: 87.71 ± 6.3 -> 90.52 ± 5.4Improved
increase views per layer from 2 to 3 (ablation)MV-AGC · PROTEINSaccuracy: 75.36 ± 3.9 -> 78.08 ± 3.4Improved
increase views per layer from 6 to 9 (ablation)MV-AGC · ENZYMESaccuracy: 62.27 ± 4.3 -> 61.10 ± 4.6Hurt
increase views per layer from 3 to 9 (ablation)MV-AGC · PROTEINSaccuracy: 78.08 ± 3.4 -> 77.81 ± 3.4No clear effect
use continuous vertex attributes instead of discrete labelsMV-AGC · ENZYMESaccuracy: 64.57 ± 5.27 -> 72.62 ± 2.63Improved
use continuous vertex attributes instead of discrete labelsMV-AGC · PROTEINSaccuracy: 78.81 ± 3.31 -> 77.66 ± 2.51Hurt
use multi-view adaptive graph convolution over single-metric GCN baselinesMV-AGC · PTC-MRaccuracy: 66.6 ± 6.9 -> 74.45 ± 3.42Improved

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