Research map / Graph learning / GNN architectures
Learning Network Dismantling Without Handcrafted Inputs
Haozhe Tian, Pietro Ferraro, Robert Noel Shorten, Mahdi Jalili, Homayoun Hamedmoghadam
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 |
|---|---|---|---|
| use MIND without handcrafted input features instead of feature-based GNN dismantlers (GDM) | MIND · Real networks, all domains | relative dismantling AUC: 104.13 -> 100.0 | Improved |
| add all-to-one attention mechanism (MIND-AM) replacing softmax-normalized attention (ablation) | MIND · Validation AUC on synthetic networks | validation dismantling AUC: p = 8.1 × 10−4 | Improved |
| add message-iteration profiles (MIND-MP) over all message-passing iterations (ablation) | MIND · Validation AUC on synthetic networks | validation dismantling AUC: p = 4.5 × 10−2 | Improved |
| use GATv2 with softmax attention as message-passing operator with constant initial embeddings (ablation) | MIND framework · Validation AUC on synthetic networks | validation dismantling AUC | Hurt |
| use GCN as message-passing operator instead of MIND encoder (ablation) | MIND framework · Validation AUC on synthetic networks | validation dismantling AUC | Hurt |
| add degree-preserving edge rewiring to diversify training networks (ablation) | MIND · Real networks, overall | dismantling AUC | Improved |
| add degree-preserving rewiring to training networks (ablation) | MIND · roads-california (modularity 0.975) | dismantling AUC: over 80% reduction in AUC | Improved |
| add degree-preserving rewiring to training networks (ablation) | MIND · munmun twitter social (assortativity -0.878) | dismantling AUC: AUC reduced by 40% | Improved |
| MIND vs exact methods on technological networks | MIND · Technological networks | dismantling AUC | Hurt |
| use handcrafted input features (GDM) instead of learned embeddings | GDM · Synthetic networks ER, CM, SBM | dismantling AUC | Hurt |
| MIND vs MS on SBM 1k nodes | MIND · Stochastic Block Model 1k nodes | dismantling AUC | No clear effect |
Closest papers by meaning
- Latent Geometry-Driven Network Automata for Complex Network Dismantling (ICLR 2026 · similarity 0.86)
- Probabilistic Graph Rewiring via Virtual Nodes (NeurIPS 2024 · similarity 0.83)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.83)
- Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning (NeurIPS 2026 · similarity 0.83)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.83)
- MIND: Multi-Task Incremental Network Distillation (AAAI 2024 · similarity 0.83)
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.
