SOTAVerified

Influence Approximation

Estimating the influence of training triples on the behavior of a machine learning model.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–7 of 7 papers

TitleStatusHype
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion ModelsCode1
Explaining Neural Matrix Factorization with Gradient RollbackCode1
ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs—0
Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data—0
Deeper Understanding of Black-box Predictions via Generalized Influence FunctionsCode0
LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation—0
On the Accuracy of Influence Functions for Measuring Group EffectsCode0
Show:102550

No leaderboard results yet.