86 citations · 161 across the 17 of their papers we have counts for
10 papers · 1 filter
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values
Shubham Sharma, Sanghamitra Dutta, Emanuele Albini +3
Feature selection is a crucial step in building machine learning models. This process is often achieved with accuracy as an objective, and can be cumbersome and computationally exp…
Causal Analysis for Robust Interpretability of Neural Networks
Ola Ahmad, Nicolas Bereux, Loïc Baret +2
Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on corr…
Task Adaptive Feature Transformation for One-Shot Learning
Imtiaz Masud Ziko, Freddy Lecue, Ismail Ben Ayed
We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entro…
Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning
Danial Dervovic, Nicolas Marchesotti, Freddy Lecue +1
We introduce a family of interpretable machine learning models, with two broad additions: Linearised Additive Models (LAMs) which replace the ubiquitous logistic link function in G…
Explainable prediction of Qcodes for NOTAMs using column generation
Krunal Kishor Patel, Guy Desaulniers, Andrea Lodi +1
A NOtice To AirMen (NOTAM) contains important flight route related information. To search and filter them, NOTAMs are grouped into categories called QCodes. In this paper, we devel…
Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions
Tom Bewley, Freddy Lecue
The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic tria…
Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach
Nicholas Halliwell, Freddy Lecue
Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifyin…
Background Knowledge Injection for Interpretable Sequence Classification
Severin Gsponer, Luca Costabello, Chan Le Van +4
Sequence classification is the supervised learning task of building models that predict class labels of unseen sequences of symbols. Although accuracy is paramount, in certain scen…
Local Score Dependent Model Explanation for Time Dependent Covariates
Xochitl Watts, Freddy Lecue
The use of deep neural networks to make high risk decisions creates a need for global and local explanations so that users and experts have confidence in the modeling algorithms. W…
Augmenting Transfer Learning with Semantic Reasoning
Freddy Lecue, Jiaoyan Chen, Jeff Z. Pan +1
Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with sema…