AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

Qitian Wu, Chenxiao Yang, Junchi Yan

NeurIPS 2021 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 10 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
replace mean pooling with GNN for new-feature embeddingsFATE-NN · Avazu CTRROC-AUC: 0.684 -> 0.710Improved
replace mean pooling with GNN for new-feature embeddingsFATE-DeepFM · Criteo CTRROC-AUC: 0.774 -> 0.783Improved
add GNN feature extrapolation over base using only observed featuresNN · Avazu CTRROC-AUC: 0.693 -> 0.710Improved
add GNN feature extrapolation over baseDeepFM · Criteo CTRROC-AUC: 0.773 -> 0.783Improved
average, KNN or pooling aggregation of observed embeddings for unseen features instead of GNNNN · UCI datasetsaccuracy: FATE 29.8% higher accuracyHurt
FATE vs incremental retraining on new features (INL-NN)FATE · UCI datasetsaccuracy: +4.1% on averageImproved
add DropEdge regularization (ablation)FATE · UCI datasetsaccuracyImproved
asynchronous updates of backbone and GNN instead of joint training (ablation)FATE · UCI datasetsaccuracyImproved
n-fold split vs k-shot sampling training (ablation)FATE · UCI datasetsaccuracyMixed

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