AI Paper Atlas

Research map / Graph learning / GNN architectures

Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks

Jiarong Xu, Renhong Huang, XIN JIANG, Yuxuan Cao, Carl Yang, Chunping Wang, Yang Yang

NeurIPS 2023 · Graph learning › GNN architectures · approach: Graph structure learning · 5 citations (OpenAlex)

Read the paper

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
add graph-property criteria to the graph selector (vs APT-G) (ablation)APT, fine-tune · dd242 node classificationmicro F1: 25.45 -> 28.62Improved
add predictive-uncertainty criterion to the selector (vs APT-P) (ablation)APT, fine-tune · dd242 node classificationmicro F1: 25.19 -> 28.62Improved
add proximal regularization w.r.t. old knowledge (vs APT-R) (ablation)APT, fine-tune · ogbarxiv node classificationmicro F1: 18.41 -> 27.40Improved
use Fisher-weighted proximal term instead of L2 (vs APT-L2) (ablation)APT, fine-tune · node classification (10 graphs)average rank: 2.6 -> 1.3Improved
add graph-property criteria to the selector (vs APT-G) (ablation)APT, freeze · node classification (10 graphs)average rank: 6.3 -> 3.8Improved
add predictive uncertainty to selector (vs APT-P) (ablation)APT, freeze · node classification (10 graphs)average rank: 6.2 -> 3.8Improved
add proximal regularization (vs APT-R) (ablation)APT, freeze · node classification (10 graphs)average rank: 5.0 -> 3.8Improved
Fisher-weighted proximal term instead of L2 (vs APT-L2) (ablation)APT, freeze · node classification (10 graphs)average rank: 4.4 -> 3.8Improved
select a subset of graphs and samples instead of pre-training on all dataGCC backbone, fine-tune · dd242 node classificationmicro F1: 19.32 -> 28.62Improved
select a subset of graphs instead of all (average over datasets, freeze)GCC backbone, freeze · node classification (10 graphs)micro F1: 9.94% average gainImproved
data selection vs training on all graphs, graph classificationGCC backbone, freeze · graph classification (3 datasets)micro F1: 7.2% average gainImproved
data selection vs training on all graphs, graph classification, fine-tuneGCC backbone, fine-tune · msrc-21 graph classificationmicro F1: 24.90 -> 24.41No clear effect

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