Research map / Graph learning / Graph self-supervised learning
Contrastive Training for Models of Information Cascades
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 |
|---|---|---|---|
| Add enhanced textual and node features to basic features (ablation) | DST unsupervised · ICWSM 2011, separated cascades | F1: 0.443 -> 0.670 | Helped |
| Add enhanced textual and node features to basic features (ablation) | DST unsupervised · ICWSM 2011, merged cascades | F1: 0.041 -> 0.045 | Helped |
| Add enhanced textual and node features to basic features (ablation) | DST unsupervised · ICWSM 2011 (tree structure enforced), merged cascades | F1: 0.073 -> 0.182 | Helped |
| Add enhanced textual and node features to basic features (ablation) | DST unsupervised · ICWSM 2011 (tree structure enforced), separated cascades | F1: 0.544 -> 0.836 | Helped |
| Use DST Enhanced instead of the naive attach-to-earliest baseline | ICWSM 2011 network inference · ICWSM 2011, separated cascades | F1: 0.608 -> 0.670 | Helped |
| Use DST Enhanced instead of the naive attach-to-earliest baseline | ICWSM 2011 network inference · ICWSM 2011 (tree structure enforced), separated cascades | F1: 0.937 -> 0.836 | Hurt |
| Train the DST with enhanced features rather than basic features (ablation) | DST supervised · Merged cascades, tree structure enforced | recall: 0.164±0.007 -> 0.455±0.011 | Helped |
Closest papers by meaning
- MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction (AAAI 2025 · similarity 0.85)
- Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection (AAAI 2024 · similarity 0.84)
- Language Model Cascades: Token-Level Uncertainty And Beyond (ICLR 2024 · similarity 0.83)
- Online Cascade Learning for Efficient Inference over Streams (ICML 2024 · similarity 0.82)
- Improved Graph Contrastive Learning for Short Text Classification (AAAI 2024 · similarity 0.82)
- A Simple Graph Contrastive Learning Framework for Short Text Classification (AAAI 2025 · similarity 0.82)
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.