9 papers
MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions
Antoine Saillenfest
Erasing concept-specific information from representations has been proven useful for mitigating bias or interpreting model decisions. The joint objective is to transform the origin…
Evaluating and Recalibrating Probabilistic Classifiers from One-Bit Threshold Queries
Roman Plaud, Antoine Saillenfest, Matthieu Labeau +2
Standard calibration evaluation and recalibration methods assume access to predicted probabilities. We study one-bit threshold access, a setting in which probabilities are hidden a…
Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference
Roman Plaud, Alexandre Perez-Lebel, Antoine Saillenfest +4
Probabilistic models are typically trained using task-agnostic objectives like log-loss, which can lead to significant errors in downstream estimation. This disconnect is especiall…
Nonlinear Concept Erasure: a Density Matching Approach
Antoine Saillenfest, Pirmin Lemberger
Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a c…
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers
Roman Plaud, Alexandre Perez-Lebel, Matthieu Labeau +2
Hierarchical classification offers an approach to incorporate the concept of mistake severity by leveraging a structured, labeled hierarchy. However, decoding in such settings freq…
Revisiting Hierarchical Text Classification: Inference and Metrics
Roman Plaud, Matthieu Labeau, Antoine Saillenfest +1
Hierarchical text classification (HTC) is the task of assigning labels to a text within a structured space organized as a hierarchy. Recent works treat HTC as a conventional multil…
Explaining Text Classifiers with Counterfactual Representations
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 feature.…
How Graph Structure and Label Dependencies Contribute to Node Classification in a Large Network of Documents
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. Our…
Role of Simplicity in Creative Behaviour: The Case of the Poietic Generator
Antoine Saillenfest, Jean-Louis Dessalles, Olivier Auber
We propose to apply Simplicity Theory (ST) to model interest in creative situations. ST has been designed to describe and predict interest in communication. Here we use ST to deriv…