Research map / Graph learning / Graph self-supervised learning
Graph Convolutional Networks Meet Markov Random Fields: Semi-Supervised Community Detection in Attribute Networks
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 |
|---|---|---|---|
| integrate MRF as an end-to-end convolutional layer in GCN | GCN · Cora | accuracy: 81.4 -> 84.3 | Helped |
| integrate MRF layer end-to-end | GCN · UAI2010 | accuracy: 16.4 -> 50.6 | Helped |
| integrate MRF layer end-to-end | GCN · NELL | accuracy: 45.4 -> 66.4 | Helped |
| two-stage MRF refinement of GCN output | GCN · Cora | accuracy: 81.4 -> 82.5 | Helped |
| two-stage MRF refinement of GCN output | GCN · Texas and Wisconsin | accuracy: 57.1 -> 55.4 (Texas) | Mixed |
| end-to-end integration instead of two-stage GCN+MRF | GCN+MRF · Cora | NMI: 64.4 -> 66.2 | Helped |
| end-to-end integration instead of two-stage GCN+MRF | GCN+MRF · UAI2010 | runtime: 185.2 -> 120.3 | Helped |
| MRFasGCN vs WSCDSM semi-supervised baseline | community detection · Texas | accuracy: 77.5 -> 71.1 | Hurt |
Closest papers by meaning
- Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning (AAAI 2020 · similarity 0.92)
- LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL (ICLR 2022 · similarity 0.90)
- Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017 · similarity 0.90)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.89)
- Incorporating Network Embedding into Markov Random Field for Better Community Detection (AAAI 2019 · similarity 0.89)
- Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification (AAAI 2024 · similarity 0.87)
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.