AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

Can Qin, Handong Zhao, Lichen Wang, Huan Wang, Yulun Zhang, Yun Fu

NeurIPS 2021 · Graph learning › Graph algorithms and clustering · approach: Graph distance and retrieval · 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
distill joint embeddings directly instead of pseudo individual embeddings (ablation)student GSC model · GED AIDSMSE (x1e-3): 1.546 -> 2.258Hurt
add knowledge distillation from teacher (ablation)student siamese model · GED AIDSMSE (x1e-3): 1.770 -> 1.546Improved
add knowledge distillation from teacher (ablation)student siamese model · GED IMDBMSE (x1e-3): 0.763 -> 0.581Improved
use both first and second order distance instead of first order only (ablation)student KD · GED AIDSMSE (x1e-3): 1.604 -> 1.546Mixed
add attention in embedding fusion network (ablation)teacher · GED AIDSMSE (x1e-3): 1.762 -> 1.601Improved
use GIN backbone instead of GCN (ablation)teacher · GED AIDSMSE (x1e-3): 2.158 -> 1.601Improved
use multi-level features instead of single level (ablation)teacher · GED AIDSMSE (x1e-3): 1.824 -> 1.601Improved
add reconstructed joint embedding regression loss L'reg (ablation)student KD · GED AIDSMSE (x1e-3): 1.711 -> 1.546Improved
use student with offline stored embeddings instead of teacher/raw-graph inferencestudent · AIDS inference timetime: 11.139s -> 0.148sImproved
student vs teacher accuracyEGSC · GED AIDSMSE (x1e-3): 1.601 -> 1.546Mixed

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