LECUE , Freddy

Global business travel spend topped record-breaking $1.2 Trillion USD in 2015, and will reach $1.6 Trillion by 2020 according to the Global Business Travel Association, the world's premier business travel and meetings trade organization. Existing expenses systems are designed for reporting expenses, their type and amount over pre-defined views...

Feature selection is a crucial step in the conception of Ma-chine Learning models, which is often performed via data-driven approaches that overlook the possibility of tappinginto the human decision-making of the model's designers andusers. We present ahuman-in-the-loopframework that inter-acts with domain experts by collecting their...

Relational Graph Convolutional Networks (RGCNs) are commonly used on Knowledge Graphs (KGs) to perform black box link prediction. Several algorithms, or explanation methods, have been proposed to explain their predictions. Evaluating performance of explanation methods for link prediction is difficult without ground truth explanations....

Nous résumons ici notre article à KCAP dont l'approche permet de générer un jeu de test comparatif et fournit des métriques pour évaluer les explications de prédictions de liens dans les graphes de connaissances par des réseaux convolutifs pour les graphes relationnels et ceci en présence de plusieurs explications possibles.

Relational Graph Convolutional Networks (RGCNs) identify relationships within a Knowledge Graph to learn real-valued embeddings for each node and edge. Recently, researchers have proposed explanation methods to interpret the predictions of these black-box models. However, comparisons across explanation methods is difficult without a common...

Relational Graph Convolutional Networks (RGCNs) are commonly applied to Knowledge Graphs (KGs) for black box link prediction. Several algorithms, or explanations methods, have been proposed to explain the predictions of this model. Recently, researchers have constructed datasets with ground truth explanations for quantitative and qualitative...

Relational Graph Convolutional Networks (RGCNs) are commonly used on Knowledge Graphs (KGs) to perform black box link prediction. Several algorithms have been proposed to explain their predictions. Evaluating performance of explanation methods for link prediction is difficult without ground truth explanations. Furthermore, there can be multiple...

Relational Graph Convolutional Networks (RGCNs) identify relationships within a Knowledge Graph to learn real-valued embeddings for each node and edge. Recently, researchers have proposed explanation methods to interpret the predictions of these blackbox models. However, comparisons across explanation methods for link prediction remains...

We summarize the paper [1] which the approach allows togenerate a benchmarks and provides metrics to evaluate explanationsof link predictions in knowledge graphs by relationalgraphs convolutional networks when several possibleexplanations do exist.

Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records. In the semantic Web, data is interpreted in ontologies and its ordered sequence is represented as an ontology stream. Our work exploits the semantics of such streams to tackle the problem of concept drift i.e., unexpected...

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 develop a tool to predict, with some explanations, a Qcode for a NOTAM. We present a way to extend the interpretable binary classification usingcolumn generation proposed...

Prototype networks (Li et al. 2018) provide explanations to users using a prototype vector; that is, a vector learned by the network representing a "typical" observation. In this work, we propose an approach that identifies relevant features in the input space used by the Prototype network. We find however that empirical evaluation of...

The development of theory, frameworks and tools for Explainable AI (XAI) is a very active area of research these days, and articulating any kind of coherence on a vision and challenges is itself a challenge. At least two sometimes complementary and colliding threads have emerged. The first focuses on the development of pragmatic tools for...

Machine learning explanation can significantly boost machine learning's application in decision making, but the usability of current methods is limited in human-centric explanation, especially for transfer learning, an important machine learning branch that aims at utilizing knowledge from one learning domain (i.e., a pair of dataset and...

Explanatory diagnosis of an ontology stream aims to explain the changes hidden in the ontology stream by a sequence of actions. In this paper, we present a framework for explanatory diagnosis of an ontology stream, which allows the actions to be uncertain. In order to capture the semantics of actions, we introduce a new update operator and...

Explainable AI is not a new field. Since at least the early exploitation of C.S. Pierce's abductive reasoning in expert systems of the 1980s, there were reasoning architectures to support an explanation function for complex AI systems, including applications in medical diagnosis , complex multi-component design, and reasoning about the real...

We predict credit applications with off-the-shelf, interchangeable black-box clas-sifiers and we explain single predictions with counterfactual explanations. Coun-terfactual explanations expose the minimal changes required on the input data to obtain a different result e.g., approved vs rejected application. Despite their effectiveness ,...

The process of managing risks of client contracts is manual and resource-consuming, particularly so for Fortune 500 companies. As an example, Accenture assesses the risk of eighty thousand contracts every year. For each contract, different types of data will be consolidated from many sources and used to compute its risk tier. For high-risk tier...