AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

Jialin Chen, Zhitao Ying

NeurIPS 2023 · Graph learning › Knowledge and temporal graphs · approach: Temporal graph neural architectures · 8 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 GINE convolution with GCN in motif encoder (ablation)TempME · Wikipedia, TGATACC-AUC: 85.81 -> 83.26Hurt
replace GINE convolution with GAT (ablation)TempME · Wikipedia, TGATACC-AUC: 85.81 -> 84.37Hurt
replace mean-pooling with adaptive pooling (ablation)TempME · Wikipedia, TGATACC-AUC: 85.81 -> 85.24Hurt
remove event anonymization (ablation)TempME · Wikipedia, TGATACC-AUC: 85.81 -> 81.47Hurt
remove time encoding (ablation)TempME · Wikipedia, TGATACC-AUC: 85.81 -> 79.42Hurt
use uniform prior instead of empirical prior (ablation)TempME · Wikipedia, GraphMixerACC-AUC: 90.15 -> 87.46Hurt
use uniform prior instead of empirical prior (ablation)TempME · Wikipedia, TGATACC-AUC: 85.81 -> 85.60Hurt
add motif embedding to TGATTGAT · USLegisaverage precision: 72.35 -> 95.31Improved
add motif embedding to TGNTGN · Enronaverage precision: 76.40 -> 75.62Hurt
add motif embedding to TGNTGN · Can.Parl.average precision: 64.23 -> 79.46Improved
add motif embedding to GraphMixerGraphMixer · UCIaverage precision: 89.13 -> 90.11Improved
TempME vs TGNNExplainer when explaining TGAT on EnronTempME · Enron, TGATACC-AUC: 82.02 -> 81.85No clear effect

Later papers that compared with this method

2 later accepted papers report TempME as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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