Research map / Graph learning / Graph self-supervised learning
Learning Diffusions without Timestamps
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 |
|---|---|---|---|
| use TWIND (status-only, MI pruning plus greedy parent search) instead of cascade-based baselines NetRate, Hyper, MulTree and S2R | diffusion network inference · LFR1-5 synthetic networks, size 100-300 | F-score | Helped |
| increase initial infection ratio from 0.05 to 0.25 | TWIND · NetSci and DUNF | F-score | No clear effect |
| increase average degree of network from 2 to 6 | TWIND · LFR6-10 | F-score | Hurt |
| increase number of diffusion processes from 50 to 250 | all algorithms incl. TWIND · NetSci and DUNF | F-score | Helped |
| use TWIND instead of NetRate, Hyper, MulTree | diffusion network inference · synthetic and real networks | runtime | Helped |
Closest papers by meaning
- Learning Diffusions under Uncertainty (AAAI 2024 · similarity 0.93)
- The Irrelevance of Influencers: Information Diffusion with Re-Activation and Immunity Lasts Exponentially Long on Social Network Models (AAAI 2024 · similarity 0.84)
- No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models (ICLR 2025 · similarity 0.84)
- Simple Guidance Mechanisms for Discrete Diffusion Models (ICLR 2025 · similarity 0.83)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · similarity 0.83)
- Learning diffusion at lightspeed (NeurIPS 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.