AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization

Shurui Gui, Meng Liu, Xiner Li, Youzhi Luo, Shuiwang Ji

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: Graph out-of-distribution generalization · 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
full LECI (label + environment adversarial independence) vs ERMGNN · GOOD-Motif basisaccuracy (%): 60.93 -> 84.56Improved
add both label and environment adversarial training to basic network (ablation)subgraph discovery network · GOOD-Motif basisaccuracy (%): 58.38 -> 84.56Improved
add both LA and EA to basic network (ablation)subgraph discovery network · GOOD-Motif sizeaccuracy (%): 65.17 -> 71.43Improved
add only label adversarial (LA) to basic network (ablation)subgraph discovery network · GOOD-Motif sizeaccuracy (%): 65.17 -> 53.57Hurt
add only environment adversarial (EA) to basic network (ablation)subgraph discovery network · GOOD-Motif sizeaccuracy (%): 65.17 -> 38.69Hurt
add only EA to basic network (ablation)subgraph discovery network · GOOD-Motif basisaccuracy (%): 58.38 -> 64.02Mixed
add pure feature shift consideration (PFSC) alone (ablation)subgraph discovery network · GOOD-CMNIST coloraccuracy (%): 33.41 -> 19.33Hurt
add LA, EA and PFSC (full LECI) to basic network (ablation)subgraph discovery network · GOOD-CMNIST coloraccuracy (%): 33.41 -> 51.80Improved
LECI environment exploitation vs GIL (IGA) on same GSAT network (ablation)GSAT · GOOD-Motif basisaccuracy (%): 55.99 -> 84.56Improved
LECI vs GIL (IGA) exploitation (ablation)GSAT · GOOD-SST2accuracy (%): 75.04 -> 83.44Improved
LECI vs GIL (IGA) exploitation (ablation)GSAT · GOOD-Twitteraccuracy (%): 60.01 -> 59.64Hurt
LECI vs best baseline on real-world datasetsGNN · GOOD-SST2accuracy (%): 81.50 -> 83.44Improved

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