List your company
ResearchFormerly WizWand

Graph Property Prediction on BACE

98.4ROC AUC<SOGk>
64.277673.136381.99590.8537Jun 10, 2021Apr 7, 2022Feb 2, 2023Nov 30, 2023Sep 26, 2024Jul 24, 2025May 21, 2026
Updated 4mo ago

Evaluation results

MethodLinks
<SOGk>Backbone=LLaMA2-7B2026.0298.4
S-CGIBDomain Adaptation=false2024.1286.51
S-CGIBDomain Adaptation=true2024.1286.46
LEAPPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1286.3
SUPTsoftPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1286.19
LEAPPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1286.16
GPF-plusPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1286.07
GPF-plusPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1286
SUPThardPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1285.94
GPFPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1285.82
RELIEFPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1285.77
LR-GMPBackbone=GIN, Pre-training Method=EdgePred2026.0485.7
GPFPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1285.36
SUPTsoftPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1285.35
RELIEFPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1285.2
SUPThardPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1285.18
FTPre-training Strategy=ContextPred, Shot Scenario=full-shot2025.1285.1
LEAPPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1284.35
SUPThardPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1284.27
GPF-plusPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1284.2
SUPTsoftPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1284.2
GPFPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1284.01
RELIEFPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1283.97
VGPBackbone=GIN, Pre-training Method=EdgePred2026.0483.62
FTPre-training Strategy=AttrMasking, Shot Scenario=full-shot2025.1283.19
FTPre-training Strategy=Infomax, Shot Scenario=full-shot2025.1282.19
MGSSL2024.1282.03
GPF-plusBackbone=GIN, Pre-training Method=EdgePred2026.0481.75
GPFBackbone=GIN, Pre-training Method=EdgePred2026.0481.57
MoAMa2024.1281.32
GROVE2024.1281.13
FTBackbone=GIN, Pre-training Method=EdgePred2026.0480.9
GraphFP2024.1280.28
EdgePredPre-Train Dataset=ZINC 2M2021.0679.9
SimSGT2024.1279.75
ContextPredPre-Train Dataset=ZINC 2M2021.0679.6
AttrMaskingPre-Train Dataset=ZINC 2M2021.0679.3
ContextPredPre-Train dataset=ZINC 2M2025.1178.8
AD-GCL-FIXPre-Train Dataset=ZINC 2M2021.0678.51
GraphCLPre-Train Dataset=ZINC 2M2021.0678.47
ContextPred2024.1278.39
LEAPPre-training Strategy=GCL, Shot Scenario=full-shot2025.1278.34
SUPThardPre-training Strategy=GCL, Shot Scenario=full-shot2025.1278.19
GPFPre-training Strategy=GCL, Shot Scenario=full-shot2025.1278.01
GPF-plusPre-training Strategy=GCL, Shot Scenario=full-shot2025.1278.01
SUPTsoftPre-training Strategy=GCL, Shot Scenario=full-shot2025.1278
Infomax2024.1277.8
GraphCL2024.1277.8
AttrMaskingPre-Train dataset=ZINC 2M2025.1177.8
EdgePredPre-Train dataset=ZINC 2M2025.1177.3
SpecMatch-CLPre-Train dataset=ZINC 2M2025.1176.93
GraphLoG2024.1276.6
RELIEFPre-training Strategy=GCL, Shot Scenario=full-shot2025.1276.03
AttrMasking2024.1275.95
GTTok.=Lap, Mode=Pad.2026.0575.94
InfoGraphPre-Train Dataset=ZINC 2M2021.0675.9
FTPre-training Strategy=GCL, Shot Scenario=full-shot2025.1275.7
GTTok.=Adj, Mode=Trunc.2026.0575.26
DeepSet2026.0575.22
SimGRACEPre-Train dataset=ZINC 2M2025.1175
JOAO2024.1274.94
GTTok.=Lap, Mode=Trunc.2026.0574.91
GTTok.=Adj, Mode=Pad.2026.0574.88
GTTok.=Comb., Mode=Trunc.2026.0574.78
GraphCLPre-Train dataset=ZINC 2M2025.1174.6
JOAOv22024.1274.38
EdgePred2024.1274.29
JOAOPre-Train dataset=ZINC 2M2025.1173.2
GIN2026.0572.73
GTTok.=Comb., Mode=Pad.2026.0572.49
No Pre-TrainPre-Train dataset=None2025.1172.4
GTTok.=RW, Mode=Trunc.2026.0570.87
GPPTBackbone=GIN, Pre-training Method=EdgePred2026.0470.85
GTTok.=RW, Mode=Pad.2026.0570.61
LEAPPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1270.33
GPPT w/o olBackbone=GIN, Pre-training Method=EdgePred2026.0470.31
No Pre-TrainPre-Train Dataset=None2021.0670.1
RELIEFPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1270.07
SUPThardPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1269.64
GIMLETBackbone=Non-LLM2026.0269.6
LEAPPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1269.45
RELIEFPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1269.37
GPF-plusPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1269.18
SUPThardPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1268.98
GPF-plusPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1268.9
SUPTsoftPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1268.75
GPFPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1268.42
GPFPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1268.26
LLaMA3-3BProtocol=Few-shot (Random)2026.0268.2
GraphPromptBackbone=GIN, Pre-training Method=EdgePred2026.0467.7
RELIEFPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1267.56
LEAPPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1267.31
SUPTsoftPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1267.05
FTPre-training Strategy=AttrMasking, Shot Scenario=50-shot2025.1266.86
SUPThardPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1266.8
FTPre-training Strategy=ContextPred, Shot Scenario=50-shot2025.1266.74
SUPTsoftPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1266.44
GPF-plusPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1266.23
FTPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1265.65
GPFPre-training Strategy=Infomax, Shot Scenario=50-shot2025.1265.59