AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

[Re] CrossWalk: Fairness-enhanced Node Representation Learning

Luca Pantea, Andrei-Eusebiu Blahovici

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 0 citations (OpenAlex)

Read the paper

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 CrossWalk instead of FairWalk and Adversarial embedding on DeepWalk embeddingsk-medoids seed selection for influence maximization · Rice-Facebook and 2-group syntheticdisparity of influenceImproved
Use CrossWalk instead of FairWalkDeepWalk embeddings for influence maximization · Twitter (3 groups)disparity and total influenceImproved
Use CrossWalk instead of FairWalk on Node2VecNode2Vec embeddings · Rice-Facebook influence maximizationdisparity of influenceImproved
Use CrossWalk instead of FairWalk with label propagationDeepWalk embeddings · Rice-Facebook node classificationdisparity of classificationImproved
Use CrossWalk instead of FairWalk for logistic regression on embeddingsDeepWalk embeddings · Rice-Facebook and Twitter link predictiondisparity across link typesImproved
Use CrossWalk instead of FairWalkDeepWalk embeddings for link prediction · Rice-Facebook and Twitter link predictionaccuracyHurt
Use CrossWalk reweighting on networks with fewer inter-group edges (ablation)CrossWalk · Synthetic 2-group graphs, varying P_interdisparity of influenceImproved
Increase bias strength p when alpha is small (ablation)CrossWalk · Synthetic graphs, P_inter 0.01 and 0.015disparity of influenceNo clear effect
Increase bias parameter p above 2 (ablation)CrossWalk · Synthetic 2-group graphdisparity of influenceImproved
Apply CrossWalk when inter-group probability is near intra-group probability (ablation)CrossWalk · Synthetic graph, P_inter 0.015disparity of influenceNo 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