Rescaled Influence Functions: Accurate Data Attribution in High Dimension
By: Ittai Rubinstein, Samuel B. Hopkins
Potential Business Impact:
Finds bad training data that tricks computers.
How does the training data affect a model's behavior? This is the question we seek to answer with data attribution. The leading practical approaches to data attribution are based on influence functions (IF). IFs utilize a first-order Taylor approximation to efficiently predict the effect of removing a set of samples from the training set without retraining the model, and are used in a wide variety of machine learning applications. However, especially in the high-dimensional regime (# params $\geq \Omega($# samples$)$), they are often imprecise and tend to underestimate the effect of sample removals, even for simple models such as logistic regression. We present rescaled influence functions (RIF), a new tool for data attribution which can be used as a drop-in replacement for influence functions, with little computational overhead but significant improvement in accuracy. We compare IF and RIF on a range of real-world datasets, showing that RIFs offer significantly better predictions in practice, and present a theoretical analysis explaining this improvement. Finally, we present a simple class of data poisoning attacks that would fool IF-based detections but would be detected by RIF.
Similar Papers
Influence Functions for Data Attribution in Linear System Identification and LQR Control
Systems and Control
Finds which training data helps robots learn best.
Revisiting Data Attribution for Influence Functions
Machine Learning (CS)
Shows which data taught a computer its answers.
Faithful and Fast Influence Function via Advanced Sampling
Machine Learning (CS)
Helps understand why computer models make certain choices.