AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Improving Hyperbolic Representations via Gromov-Wasserstein Regularization

Yifei Yang, Wonjun Lee, Dongmian Zou, Gilad Lerman

ECCV 2024 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 5 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
add Gromov-Monge regularization to hyperbolic ProtoNethyperbolic ProtoNet (ResNet18) · MiniImageNet 5-Shot 5-Wayaccuracy (%): 68.43 -> 71.64Improved
add GW regularization to hyperbolic ProtoNet (Conv4)hyperbolic ProtoNet · CUB 1-Shot 5-Wayaccuracy (%): 64.66 -> 68.67Improved
add GW regularization to hyperbolic ProtoNet (Conv4)hyperbolic ProtoNet · CUB 5-Shot 5-Wayaccuracy (%): 80.29 -> 80.54No clear effect
add GW regularization to HNN for node classificationHNN · Disease node classificationF1 (%): 58.40 -> 65.62Improved
add GW regularization to HyboNet for node classificationHyboNet · Wisconsin node classificationF1 (%): 74.07 -> 80.87Improved
add GW regularization to HGCN for link predictionHGCN · Cora link predictionAUC (%): 93.37 -> 93.48No clear effect
add GW regularization to HGCN for link predictionHGCN · Airport link predictionAUC (%): 93.42 -> 95.81Improved
add GW regularization (training cost)hyperbolic ProtoNet (ResNet18, MiniImageNet 5-Shot) · per-epoch runtime (s)runtime: 43.2 -> 49.2Hurt
add GW regularization to reduce GW distance between HNN input and output featureshyperbolic ProtoNet Conv4 · CUB 5-Shot 5-WayGW distance: 47833.570 -> 1.575Improved
vary beta hyperparameter around chosen value (ablation)GW regularization · Disease-LP and Disease-NCperformanceNo clear effect

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