Konstantinos Georgatzis — accepted AI-conference papers

2021

FIMAP: Feature Importance by Minimal Adversarial Perturbation

Matt Chapman-Rounds, Umang Bhatt, Erik Pazos, Marc-Andre Schulz, Konstantinos Georgatzis

AAAI 2021technical

Instance-based model-agnostic feature importance explanations (LIME, SHAP, L2X) are a popular form of algorithmic transparency. These methods generally return either a weighting or subset of input features as an explanation for the classification of an instance. An alternative literature argues inst…

Cited by 20 Source ↗PDF ↗Scholar ↗

2020

DYNOTEARS: Structure Learning from Time-Series Data

Roxana Pamfil, Nisara Sriwattanaworachai, Shaan Desai, Philip Pilgerstorfer, Konstantinos Georgatzis, Paul Beaumont +1

AISTATS 2020poster

We revisit the structure learning problem for dynamic Bayesian networks and propose a method that simultaneously estimates contemporaneous (intra-slice) and time-lagged (inter-slice) relationships between variables in a time-series. Our approach is score-based, and revolves around minimizing a penal…

Cited by 251 Source ↗PDF ↗Scholar ↗