Influence Functions: Why One Training Point Can Move a Prediction
This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.
A model makes a surprising prediction. You want to know why. The usual answers point to features, attention weights, or a saliency map. Those answers explain the input. They do not explain the training data. Influence functions answer a different question: which training examples pushed the model t…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-16 09:23 · DEV Community — Machine Learning
Influence Functions: Why One Training Point Can Move a Prediction