AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Theoretical and Practical Perspectives on what Influence Functions Do

Andrea Schioppa, Katja Filippova, Ivan Titov, Polina Zablotskaia

NeurIPS 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Conjugate Residual instead of Conjugate Gradient for inverse Hessian-vector products in HIF (ablation)Hessian influence function (HIF) · BERT/ResNetPearson correlation R(t)Improved
retrain longer after the checkpoint (time since checkpoint increases)influence scores (TracIn, HIF) · BERT SST2 and ResNet CIFAR10Pearson correlation R(t)Hurt
Proponents-correction and Opponents-tuning instead of random relabeling baselineBERT · SST2success rate of correcting mis-predictionsImproved
Proponents-correction instead of random relabeling baselineResNet · CIFAR10success rate: +2%Improved
Proponents-correction instead of baselineResNet · CIFAR10steps to correct: 6%Improved
Opponents-tuning instead of baselineResNet · CIFAR10success rate: 54%No clear effect
fine-tune ResNet with SGD vs BERT with Adam; slower parameter divergenceinfluence scores · ResNet CIFAR10Pearson correlation R(t): 0.3Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy