Deeper Understanding of Black-box Predictions via Generalized Influence Functions

원문 초록

Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect that the fragility comes from the first-order approximation which may cause nuisance changes in parameters irrelevant to the examined data. However, simply computing influence from the chosen parameters can be misleading, as it fails to nullify the hidden effects of unselected parameters on the analyzed data. Thus, our approach introduces generalized IFs, precisely estimating target parameters' influence while nullifying nuisance gradient changes on fixed parameters. We identify target update parameters closely associated with the input data by the output- and gradient-based parameter selection methods. We verify the generalized IFs with various alternatives of IFs on the class removal and label change tasks. The experiments align with the "less is more" philosophy, demonstrating that updating only 5\% of the model produces more accurate results than other influence functions across all tasks. We believe our proposal works as a foundational tool for optimizing models, conducting data analysis, and enhancing AI interpretability beyond the limitation of IFs. Codes are available at https://github.com/hslyu/GIF.