AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks

Guangmo Tong

NeurIPS 2020 · Learning theory and algorithms › Combinatorial and search optimization · approach: Unsupervised neural combinatorial optimization · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
increase the number of random subgraph features (ablation)StratLearner · Kroneckerperformance ratio: 0.699 { (8E-3)} -> 0.810 { (9E-3)}Improved
increase the number of random subgraph features (ablation)StratLearner · Power-lawperformance ratio: 0.707 { (1E-2)} -> 0.902 { (8E-3)}Improved
increase the number of random subgraph features (ablation)StratLearner · Erdős-Rényiperformance ratio: 0.661 { (2E-2)} -> 0.892{ (3E-3)}Improved
increase training examples from 270 to 2160 (ablation)StratLearner · Kroneckerperformance ratio: 0.699 { (8E-3)} -> 0.701 { (1E-2)}No clear effect
increase sampled-edge probability from 0.01 to 0.1 (ablation)StratLearner · Power-lawperformance ratio: 0.725 -> 0.931Improved
increase sampled-edge probability from 0.01 to 0.1 (ablation)StratLearner · Erdős-Rényiperformance ratio: 0.714 -> 0.866Improved
increase sampled-edge probability from 0.01 to 0.1 (ablation)StratLearner · Kroneckerperformance ratio: 0.708 -> 0.806Improved
use the full graph as the sole feature (ablation)StratLearner · Kroneckerperformance ratio: 0.708 -> 0.775Hurt
sample subgraphs using prior knowledge of the diffusion model (ablation)StratLearner · Kroneckerperformance ratio: 0.708 -> 0.961Improved
use 400 StratLearner features instead of the strongest baselineStratLearner · Kroneckerperformance ratio: 0.670 -> 0.759Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy