List your company
ResearchFormerly WizWand

Text Classification on Amazon (accuracy)

96.45AccuracyGNNAVI-GCN
32.43849.056565.67582.2935Feb 18, 2024Jun 20, 2024Oct 22, 2024Feb 22, 2025Jun 26, 2025Oct 27, 2025Feb 28, 2026
Updated 8mo ago

Evaluation results

MethodLinks
GNNAVI-GCNBackbone=Llama2, k (training examples per class)=200, #Param=16.8M2024.0296.45
FPFTBackbone=Llama2, k (training examples per class)=200, #Param=6.7B2024.0296.12
GNNAVI-SAGEBackbone=Llama2, k (training examples per class)=200, #Param=33.6M2024.0295.96
FPFTBackbone=Llama2, k (training examples per class)=5, #Param=6.7B2024.0295.86
LORABackbone=Llama2, k (training examples per class)=200, #Param=4.2M2024.0295.8
GNNAVI-SAGEBackbone=Llama2, k (training examples per class)=5, #Param=33.6M2024.0295.66
ICLBackbone=Llama2, k (training examples per class)=02024.0294.98
GNNAVI-GCNBackbone=Llama2, k (training examples per class)=5, #Param=16.8M2024.0294
GNNAVI-SAGEBackbone=GPT2-XL, k (training examples per class)=200, #Param=5.1M2024.0293.44
AdapterBackbone=GPT2-XL, k (training examples per class)=200, #Param=15.4M2024.0292.3
ICLBackbone=Llama2, k (training examples per class)=52024.0292.3
LORABackbone=Llama2, k (training examples per class)=5, #Param=4.2M2024.0291.8
GCPannotation budget=20%2026.0291.62
AdapterBackbone=GPT2-XL, k (training examples per class)=5, #Param=15.4M2024.0291.45
GNNAVI-GCNBackbone=GPT2-XL, k (training examples per class)=5, #Param=2.6M2024.0290.9
CALannotation budget=20%2026.0290.54
ALPSannotation budget=20%2026.0289.87
BADGEannotation budget=20%2026.0289.81
Entropy Samplingannotation budget=20%2026.0289.63
CoreSet (k-center)annotation budget=20%2026.0289.32
Disagreement (Vote Entropy)annotation budget=20%2026.0289.21
GNNAVI-GCNBackbone=GPT2-XL, k (training examples per class)=200, #Param=2.6M2024.0289.2
Least Confidenceannotation budget=20%2026.0288.94
LORABackbone=GPT2-XL, k (training examples per class)=5, #Param=2.5M2024.0288.8
GNNAVI-SAGEBackbone=GPT2-XL, k (training examples per class)=5, #Param=5.1M2024.0288.66
Way-DEWays=5, Shots=5-shot2026.0287.4
Shot-DEWays=5, Shots=5-shot2026.0286.9
Randomannotation budget=20%2026.0286.6
MLADAWays=5, Shots=5-shot2026.0286
SPCNetWays=5, Shots=5-shot2026.0285.3
LDS-PNWays=5, Shots=5-shot2026.0285.1
ProtoVerbWays=5, Shots=5-shot2026.0284.7
TARTWays=5, Shots=5-shot2026.0284.3
ContrastNetWays=5, Shots=5-shot2026.0283.6
LORABackbone=GPT2-XL, k (training examples per class)=200, #Param=2.5M2024.0282
LDS-PNWays=5, Shots=1-shot2026.0281.8
DS-FSLWays=5, Shots=5-shot2026.0281.1
LaSAMLWays=5, Shots=5-shot2026.0279.1
SPCNetWays=5, Shots=1-shot2026.0276.3
Shot-DEWays=5, Shots=1-shot2026.0276.1
Way-DEWays=5, Shots=1-shot2026.0276.1
FPFTBackbone=GPT2-XL, k (training examples per class)=200, #Param=1.6B2024.0274.82
TARTWays=5, Shots=1-shot2026.0273.7
ContrastNetWays=5, Shots=1-shot2026.0273.5
FPFTBackbone=GPT2-XL, k (training examples per class)=5, #Param=1.6B2024.0273
ProtoVerbWays=5, Shots=1-shot2026.0272.4
MLADAWays=5, Shots=1-shot2026.0268.4
DS-FSLWays=5, Shots=1-shot2026.0262.6
LaSAMLWays=5, Shots=1-shot2026.0262.2
PrefixBackbone=GPT2-XL, k (training examples per class)=5, #Param=6.1M2024.0260
PrefixBackbone=GPT2-XL, k (training examples per class)=200, #Param=6.1M2024.0259.8
ICLBackbone=GPT2-XL, k (training examples per class)=52024.0253.67
ICLBackbone=GPT2-XL, k (training examples per class)=02024.0253.32
PrefixBackbone=Llama2, k (training examples per class)=200, #Param=39.3M2024.0252.28
PNWays=5, Shots=5-shot2026.0252.1
AdapterBackbone=Llama2, k (training examples per class)=5, #Param=198M2024.0249.45
AdapterBackbone=Llama2, k (training examples per class)=200, #Param=198M2024.0249.45
PrefixBackbone=Llama2, k (training examples per class)=5, #Param=39.3M2024.0249.36
MAMLWays=5, Shots=5-shot2026.0247.1
INWays=5, Shots=5-shot2026.0241.3
MAMLWays=5, Shots=1-shot2026.0239.6
PNWays=5, Shots=1-shot2026.0237.6
INWays=5, Shots=1-shot2026.0234.9