AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Graphite: Iterative Generative Modeling of Graphs

Aditya Grover, Aaron Zweig, Stefano Ermon

ICML 2019 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 35 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 an iterative learned graph-refinement decoder instead of the inner-product decoderGraphite-VAE · Erdos-Renyi, Ego, Regular, Geometric, Power Law, Barabasi-Albertnegative log-likelihood: 273.82 -> 270.22; 273.76 -> 270.70; 275.29 -> 266.54; 274.09 -> 269.71; 278.86 -> 263.92; 274.4 -> 268.73Improved
Use iterative graph refinement rather than an inner-product-only decoderLink prediction, featureless citation networks · Cora, Citeseer, PubmedAUC: Cora: 90.1 -> 91.5; Citeseer: 92.0 -> 93.5; Pubmed: 92.3 -> 94.6Mixed
Use iterative graph refinement rather than an inner-product-only decoderLink prediction with node features · Cora*, Citeseer*, Pubmed*AUC: 94.1 -> 94.7; 96.7 -> 97.3; 95.5 -> 97.4Mixed
Combine the Graphite objective with supervised GCN trainingGCN node classifier · Cora*, Citeseer*, Pubmed*accuracy: 81.5 -> 82.1; 70.3 -> 71.0; 79.0 -> 79.3Improved
Train using edge subsampling for Monte Carlo objective evaluationGraphite · Cora, Citeseer, PubmedAUC: 90.5 vs 91.5; 92.5 vs 93.5; 93.1 vs 94.6Hurt
Use an embedding skip connection combining the initial and refined embeddingsGraphite · Link predictionAUCImproved

Later papers that compared with this method

2 later accepted papers report Graphite 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