1 code implementation • 1 Feb 2024 • Pirmin Lemberger, Antoine Saillenfest
One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one categorical feature.
1 code implementation • 10 May 2023 • Jean Vassoyan, Jill-Jênn Vie, Pirmin Lemberger
Our model is a sequential recommender system based on a graph neural network, which we evaluate on a population of simulated learners.
1 code implementation • 3 Apr 2023 • Pirmin Lemberger, Antoine Saillenfest
We introduce a new dataset named WikiVitals which contains a large graph of 48k mutually referred Wikipedia articles classified into 32 categories and connected by 2. 3M edges.
no code implementations • 8 Jul 2020 • Pirmin Lemberger, Denis Oblin
Statisticians have warned us since the early days of their discipline that experimental correlation between two observations by no means implies the existence of a causal relation.
no code implementations • 25 May 2020 • Pirmin Lemberger
Text summarization is an NLP task which aims to convert a textual document into a shorter one while keeping as much meaning as possible.
no code implementations • 27 Jan 2020 • Pirmin Lemberger, Ivan Panico
Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions.
no code implementations • 5 Apr 2017 • Pirmin Lemberger
Why do large neural network generalize so well on complex tasks such as image classification or speech recognition?