Research map / Graph learning / Graph self-supervised learning
Multi-view adaptive graph convolutions for graph classification
Nikolas Adaloglou, Nicholas Vretos, Petros Daras
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 views per layer from 2 to 6 (ablation) | MV-AGC · ENZYMES | accuracy: 56.02 ± 6.3 -> 62.27 ± 4.3 | Improved |
| increase views per layer from 2 to 9 (ablation) | MV-AGC · MUTAG | accuracy: 87.71 ± 6.3 -> 90.52 ± 5.4 | Improved |
| increase views per layer from 2 to 3 (ablation) | MV-AGC · PROTEINS | accuracy: 75.36 ± 3.9 -> 78.08 ± 3.4 | Improved |
| increase views per layer from 6 to 9 (ablation) | MV-AGC · ENZYMES | accuracy: 62.27 ± 4.3 -> 61.10 ± 4.6 | Hurt |
| increase views per layer from 3 to 9 (ablation) | MV-AGC · PROTEINS | accuracy: 78.08 ± 3.4 -> 77.81 ± 3.4 | No clear effect |
| use continuous vertex attributes instead of discrete labels | MV-AGC · ENZYMES | accuracy: 64.57 ± 5.27 -> 72.62 ± 2.63 | Improved |
| use continuous vertex attributes instead of discrete labels | MV-AGC · PROTEINS | accuracy: 78.81 ± 3.31 -> 77.66 ± 2.51 | Hurt |
| use multi-view adaptive graph convolution over single-metric GCN baselines | MV-AGC · PTC-MR | accuracy: 66.6 ± 6.9 -> 74.45 ± 3.42 | Improved |
Closest papers by meaning
- MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification (NeurIPS 2025 · similarity 0.89)
- Graph Multi-Convolution and Attention Pooling for Graph Classification (TPAMI 2024 · similarity 0.89)
- Adaptive Graph Convolutional Neural Networks (AAAI 2018 · similarity 0.88)
- SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · similarity 0.87)
- Co-GCN for Multi-View Semi-Supervised Learning (AAAI 2020 · similarity 0.87)
- Geometry-Aware Edge Pooling for Graph Neural Networks (NeurIPS 2025 · similarity 0.86)
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.
