most citedPTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization

8 citations · 8 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025

Improving Deep Tabular Learning

Sivan Sarafian, Yehudit Aperstein

Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and li…

cs.LG2025★ 8 cited

PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization

Assaf Lahiany, Yehudit Aperstein

For many practical applications, a high computational cost of inference over deep network architectures might be unacceptable. A small degradation in the overall inference accuracy…