Amirata Ghorbani
9 papers · 2019–2023 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (25) π§ Keyword Pioneer
π
Grand Slam
π
Keyword Champion
(4)
π₯
Mega-Team Β· Squad
π
Conference Pioneer
β
The Questioner
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(5)
Application Areas
(5)
Core AI Β· Artificial Intelligence
(5)
Optimization & Theory
(4)
Core Methods
(3)
Learning Types Β· Machine Learning
(3)
Deep Learning
(2)
Computer Science
(1)
Computer Vision
(1)
Mathematics & Optimization
(1)
Analysis
(1)
Applications
(1)
Core AI Β· Computer Vision
(1)
Learning Types Β· Deep Learning
(1)
Keywords
feature importance
(4)
data augmentation
(3)
shapley value
(3)
neural network interpretability
(2)
adversarial robustness
(2)
data valuation
(2)
adversarial attack
(2)
benchmark suite
(1)
model evaluation
(1)
neural network security
(1)
model robustness
(1)
feature selection
(1)
false discovery rate
(1)
game theory
(1)
feature attribution
(1)
domain adaptation
(1)
neural network interpretation
(1)
monte carlo estimation
(1)
visual concept
(1)
concept-based explanation
(1)
Papers
DataPerf: Benchmarks for Data-Centric AI Development
NeurIPS 2023
How Does Mixup Help With Robustness and Generalization?
ICLR 2021
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
AISTATS 2021
A Distributional Framework For Data Valuation
ICML 2020
Neuron Shapley: Discovering the Responsible Neurons
NeurIPS 2020
Data Shapley: Equitable Valuation of Data for Machine Learning
ICML 2019
Interpretation of Neural Networks Is Fragile
AAAI 2019
Knockoffs for the Mass: New Feature Importance Statistics with False Discovery Guarantees
AISTATS 2019
Towards Automatic Concept-based Explanations
NeurIPS 2019