Search Results for author:
Found 4 papers, 1 papers with code
Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers
We compare TOKI with a naive baseline based solely on model confidence and TOKI-guided adversarial attack method with A2T, a SOTA adversarial attack method.
Automated Trustworthiness Testing for Machine Learning Classifiers
Our hypothesis is that a prediction is trustworthy if the words in its explanation are semantically related to the predicted class.
SGP-DT: Semantic Genetic Programming Based on Dynamic Targets
The evolution in each run is guided by a new (dynamic) target based on the residual errors.
Expeditious Generation of Knowledge Graph Embeddings
Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space.
Ranked #1 on
Link Prediction
on AKSW-bib
