Clustered Compositional Embeddings

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Miscellaneous2 results

Click-Through Rate PredictiononCriteo
AUC· 2022-10-12
0.806
best: 0.8163 (QNN-α)
Clustering the Sketch: A Novel Approach to Embedding Table Compression arXiv:2210.05974
Click-Through Rate PredictiononCriteo
Log Loss· 2022-10-12
0.449
best: 0.4358 (QNN-α)
Clustering the Sketch: A Novel Approach to Embedding Table Compression arXiv:2210.05974