AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

A Graph Convolutional Network with Adaptive Graph Generation and Channel Selection for Event Detection

AAAI 2022 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 9 citations (OpenAlex)

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 changedWhereMeasuredEffect
use adaptive graph generation with gated multi-channel convolutionAGGED · ACE2005 testF1: 78.6 -> 79.9Helped
add multi-channel selection (ablation)AGGED · ACE2005 testF1: 79.4 -> 79.9Helped
add information gating (ablation)AGGED · ACE2005 testF1: 78.7 -> 79.9Helped
add both multi-channel selection and information gating (ablation)AGGED · ACE2005 testF1: 79.0 -> 79.9Helped
use adaptive graph generation instead of a static dependency parse graph (ablation)AGGED · ACE2005 testF1: 78.3 -> 79.9Helped
pretrain the graph generator with a burn-in phase (ablation)AGGED · ACE2005 testF1: 77.9 -> 79.9Helped
increase the number of information channels from fewer than 3 to 3 (ablation)AGGED · ACE2005 validation and testF1Helped
increase the number of information channels beyond 3 (ablation)AGGED · ACE2005 validation and testF1Hurt

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