AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Kaidi Cao, Bahare Fatemi, Michael Burrows, Charith Mendis, Bryan Perozzi

NeurIPS 2023 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 1 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
train with ListMLE ranking loss instead of MSE (ablation)EarlySAGE · Tile:XLA testtop-1 error %: 22.0 -> 9.1Improved
train with ListMLE ranking loss instead of MSE (ablation)EarlyGCN · Tile:XLA testtop-1 error %: 21.0 -> 11.4Improved
train with ListMLE ranking loss instead of MSE (ablation)LateGCN · Tile:XLA testtop-1 error %: 67.0 -> 17.4Improved
early-join config features with node features instead of late-join (ablation)SAGE, ListMLE · Tile:XLA testtop-1 error %: 71.8 -> 9.1Improved
early-join instead of late-join (ablation)GCN, ListMLE · Tile:XLA testtop-1 error %: 17.4 -> 11.4Improved
use GraphSAGE instead of GCN (ablation)EarlyJoin ListMLE · Tile:XLA testtop-1 error %: 11.4 -> 9.1No clear effect
remove GNN (MLP baseline) (ablation)ListMLE · Tile:XLA testtop-1 error %: 9.1 -> 52.9Hurt
train on full graph instead of graph segments (GST) (ablation)layout model · Layout:XLA:Random testKendall tau: 0.32 -> 0.37Improved
train on full graph instead of graph segments (GST) (ablation)layout model · Layout:XLA:Random testtop-1 error %: 8.1 -> 12.2Hurt
MSE loss instead of ranking loss (ablation)layout model · Layout:XLA:Random testKendall tau: 0.32 -> 0.31No clear effect
default search space instead of random search spacelayout model · Layout:XLA testKendall tau: 0.34 -> 0.21Hurt
XLA graphs instead of NLP graphslayout model · Layout:Random testKendall tau: 0.53 -> 0.34Hurt

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