AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Deep Hierarchical Graph Convolution for Election Prediction from Geospatial Census Data

Mike Li, Elija Perrier, Chang Xu

AAAI 2019 · Graph learning › Knowledge and temporal graphs · approach: Spatio-temporal graph traffic forecasting · 15 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
use graph convolution over SA1 neighbours instead of Random ForestElection 2PP prediction · 80% trainRMSE: 7.75 -> 2.37Improved
add hierarchical SA2 graph (V2) to standard GCNNGraph-CNN · 80% trainRMSE: 2.37 -> 2.20Improved
add hierarchical SA2 graph (V2) to standard GCNNGraph-CNN · 20% trainRMSE: 3.20 -> 2.81Improved
add hierarchical SA2 graph (V5) to standard GCNNGraph-CNN · 10% trainRMSE: 3.94 -> 3.39Improved
use more complex variants (V4/V5) instead of simple projection V2 (ablation)Hierarchical GCNN · 80% trainRMSE: 2.20 -> 2.69Hurt
use more complex variant V5 instead of V2 with 10% training data (ablation)Hierarchical GCNN · 10% trainRMSE: 3.45 -> 3.39Improved
add Mahalanobis distance learning to projection edges (ablation)Hierarchical GCNN · 80% trainRMSE: 2.20 -> 2.15No clear effect
add Mahalanobis distance learning to projection edges (ablation)Hierarchical GCNN · 10% trainRMSE: 3.45 -> 3.43No clear effect
add third SA3 level to V5 (ablation)Hierarchical GCNN (V5) · 10% trainRMSE: 3.39 -> 3.28Improved
add third SA3 level to V2 (ablation)Hierarchical GCNN (V2) · 80% trainRMSE: 2.20 -> 2.52Hurt
add third SA3 level with graph convolution to V2 (ablation)Hierarchical GCNN (V2) · 10% trainRMSE: 3.45 -> 3.37Improved
graph convolution at SA2 level instead of direct projection (ablation)Hierarchical GCNN · all splitsRMSEImproved

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