Research map / Graph learning / Graph self-supervised learning
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
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 |
|---|---|---|---|
| maximize mutual information between whole-graph and multiscale patch representations | InfoGraph · graph classification benchmarks | accuracy | Mixed |
| add unsupervised InfoGraph loss to the supervised objective using one encoder | enn-s2s on QM9 · QM9 molecular property prediction | error ratio | Mixed |
| use separate supervised and unsupervised encoders and maximize mutual information between their intermediate representations | InfoGraph* on QM9 · QM9 molecular property prediction | error ratio | Helped |
| replace supervised-output matching with mutual-information transfer across encoder representations | semi-supervised graph prediction · QM9 molecular property prediction | error ratio | Helped |
Closest papers by meaning
- Graph of Graphs: A New Knowledge Representation Mechanism for Graph Learning (Student Abstract) (AAAI 2023 · similarity 0.91)
- Learning Graph Representation via Graph Entropy Maximization (ICML 2024 · similarity 0.91)
- Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021 · similarity 0.90)
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.87)
- Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach (AAAI 2025 · similarity 0.87)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 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.