AI RESEARCH

LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution

arXiv CS.LG

Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretically grounded family of TDA methods and exploit gradients. To overcome the scalability challenge arising from gradient computation, the most popular strategy is random projection (e.g., TRAK, LoGRA).