conftrace_

influence function

143 papers

Explore in graph

Also known as

IF

Co-occurring keywords

large language model (13587) training datum (124) machine unlearning (290) model interpretation (93) model interpretability (519) data attribution (16) neural network (6616) data selection (221) model debugging (24) training data attribution (10)

Papers

A General Framework for Auditing Differentially Private Machine Learning NIPS 2022
Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations NIPS 2022
JAWS: Auditing Predictive Uncertainty Under Covariate Shift NIPS 2022
Repairing Neural Networks by Leaving the Right Past Behind NIPS 2022
If Influence Functions are the Answer, Then What is the Question? NIPS 2022
Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals with Application to Proximal Causal Inference AISTATS 2022
Understanding Programmatic Weak Supervision via Source-aware Influence Function NIPS 2022
Finding Influential Instances for Distantly Supervised Relation Extraction COLING 2022
The Trade-offs of Domain Adaptation for Neural Language Models ACL 2022
Few Clean Instances Help Denoising Distant Supervision COLING 2022
First is Better Than Last for Language Data Influence NIPS 2022
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting NIPS 2022
Semiparametric Inference For Causal Effects In Graphical Models With Hidden Variables JMLR 2022
Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective NIPS 2022
Exploring Example Influence in Continual Learning NIPS 2022
Data poisoning attacks on off-policy policy evaluation methods UAI 2022
Offline change detection under contamination UAI 2022
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation IJCNLP 2021
Understanding Instance-based Interpretability of Variational Auto-Encoders NIPS 2021
Estimating Identifiable Causal Effects through Double Machine Learning AAAI 2021
Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging EMNLP 2021
HILDIF: Interactive Debugging of NLI Models Using Influence Functions ACL 2021
HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks AAAI 2021
Outlier Impact Characterization for Time Series Data AAAI 2021