Formula for Performance Gap Recovered (PGR)

An AI research team conducts two separate experiments to improve a powerful model's performance by having it learn from a less powerful one. The results are as follows:

• Experiment A: The less powerful model scores 50% on a task. The powerful model, after learning from the less powerful one, scores 70%. The powerful model's maximum possible score on this task is 90%.
• Experiment B: The less powerful model scores 70% on a different task. The powerful model, after learning from the less powerful one, scores 78%. The powerful model's maximum possible score on this task is 80%.

Based on these results, which experiment demonstrates a more effective transfer of knowledge from the less powerful model to the more powerful one, in terms of closing the potential performance gap?

Evaluating Knowledge Transfer Effectiveness

Evaluating Performance Gains in Model Training

Interpretation and Empirical Results of Performance Gap Recovered