Research map / Graph learning / Graph algorithms and clustering
Learning Steady-States of Iterative Algorithms over Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace S2V-degree (T=5) with SSE | S2V-degree · Transductive PageRank BA m=1, 10m nodes | MAE: 0.4954 -> 0.0162 | Helped |
| replace S2V-degree (T=5) with SSE | S2V-degree · Transductive PageRank BA m=4, 10m nodes | MAE: 0.1223 -> 0.0083 | Helped |
| replace S2V-degree with SSE | S2V-degree · Inductive PageRank BA m=1, 10m nodes | MAE: 0.5254 -> 0.0202 | Helped |
| increase graph size from 1k to 10m nodes | S2V-degree · Transductive PageRank BA m=1 | MAE: 0.0652 -> 0.4954 | Hurt |
| increase graph size from 1k to 10m nodes | SSE · Transductive PageRank BA m=1 | MAE: 0.0041 -> 0.0162 | Hurt |
| harder graphs with m=1 instead of m=4 | SSE · Transductive PageRank, 10m nodes | MAE: 0.0083 -> 0.0162 | Hurt |
| replace GCN/structure2vec with SSE | GCN · Graph connectivity | accuracy: 96% -> 99% | Helped |
| increase propagation steps T of GCN (ablation) | GCN · Graph connectivity | accuracy | Helped |
| replace GCN with SSE | GCN · Amazon multi-label 1% labeled | Micro-F1: 70.39 -> 78.36 | Helped |
| replace GCN with SSE | GCN · Amazon multi-label 9% labeled | Micro-F1: 85.68 -> 87.13 | Helped |
| replace GraphSAGE-LSTM with SSE | GraphSAGE-LSTM · PPI | Micro-F1: 0.612 -> 0.836 | Helped |
| increase PageRank T for GCN (larger T) (ablation) | GCN · PageRank | accuracy | No clear effect |
Closest papers by meaning
- Convergent Graph Solvers (ICLR 2022 · similarity 0.89)
- Learning Combinatorial Optimization Algorithms over Graphs (NeurIPS 2017 · similarity 0.88)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.86)
- Algorithms and Hardness for Active Learning on Graphs (ICML 2025 · similarity 0.86)
- Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph (ICML 2024 · similarity 0.85)
- Learning Graph Representation via Graph Entropy Maximization (ICML 2024 · similarity 0.85)
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.