no code implementations • 22 Nov 2022 • Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier.
no code implementations • 13 Oct 2022 • Aleksey Buzmakov, Tatiana Makhalova, Sergei O. Kuznetsov, Amedeo Napoli
In this paper, we revisit pattern mining and study the distribution underlying a binary dataset thanks to the closure structure which is based on passkeys, i. e., minimum generators in equivalence classes robust to noise.
no code implementations • 5 Aug 2021 • Guilherme Alves, Maxime Amblard, Fabien Bernier, Miguel Couceiro, Amedeo Napoli
Unintended biases in machine learning (ML) models are among the major concerns that must be addressed to maintain public trust in ML.
no code implementations • 20 Apr 2021 • Claire Theobald, Bastien Arcelin, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
We show that while a convolutional network can be trained to correctly estimate well calibrated aleatoric uncertainty, -- the uncertainty due to the presence of noise in the images -- it is unable to generate a trustworthy ellipticity distribution when exposed to previously unseen data (i. e. here, blended scenes).
no code implementations • 3 Feb 2021 • Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving... BNN assume a prior over the weights of a neural network instead of point estimates, enabling in this way the estimation of both aleatoric and epistemic uncertainty of the model prediction. Moreover, a particular type of BNN, namely MC Dropout, assumes a Bernoulli distribution on the weights by using Dropout. Several attempts to optimize the dropout rate exist, e. g. using a variational approach. In this paper, we present a new method called "Dropout Regulation" (DR), which consists of automatically adjusting the dropout rate during training using a controller as used in automation. DR allows for a precise estimation of the uncertainty which is comparable to the state-of-the-art while remaining simple to implement.
no code implementations • 30 Nov 2020 • Tatiana Makhalova, Sergei O. Kuznetsov, Amedeo Napoli
Pattern mining is well established in data mining research, especially for mining binary datasets.
1 code implementation • 11 Nov 2020 • Pierre Monnin, Chedy Raïssi, Amedeo Napoli, Adrien Coulet
In this article, we propose to match nodes within a knowledge graph by (i) learning node embeddings with Graph Convolutional Networks such that similar nodes have low distances in the embedding space, and (ii) clustering nodes based on their embeddings, in order to suggest alignment relations between nodes of a same cluster.
no code implementations • 1 Nov 2020 • Guilherme Alves, Vaishnavi Bhargava, Miguel Couceiro, Amedeo Napoli
To illustrate, we will revisit the case of "LimeOut" that was proposed to tackle "process fairness", which measures a model's reliance on sensitive or discriminatory features.
no code implementations • 6 Oct 2020 • Tatiana Makhalova, Aleksey Buzmakov, Sergei O. Kuznetsov, Amedeo Napoli
The closure structure allows one to understand the topology of the dataset in the whole and the inherent complexity of the data.
1 code implementation • 17 Jul 2020 • Pierre Monnin, Emmanuel Bresso, Miguel Couceiro, Malika Smaïl-Tabbone, Amedeo Napoli, Adrien Coulet
Features mined from knowledge graphs are widely used within multiple knowledge discovery tasks such as classification or fact-checking.
no code implementations • 17 Jun 2020 • Vaishnavi Bhargava, Miguel Couceiro, Amedeo Napoli
To achieve both, we draw inspiration from "dropout" techniques in neural based approaches, and propose a framework that relies on "feature drop-out" to tackle process fairness.
1 code implementation • 19 Feb 2020 • Pierre Monnin, Miguel Couceiro, Amedeo Napoli, Adrien Coulet
In particular, units should be matched within and across sources, and their level of relatedness should be classified into equivalent, more specific, or similar.
no code implementations • 28 Mar 2017 • Aleksey Buzmakov, Sergei O. Kuznetsov, Amedeo Napoli
One of the first constraints proposed in pattern mining is support (frequency) of a pattern in a dataset.
no code implementations • 2 Jun 2015 • Aleksey Buzmakov, Sergei O. Kuznetsov, Amedeo Napoli
In this paper we consider stability and $\Delta$-measure, which are nonmonotonic constraints, and apply them to interval tuple datasets.
no code implementations • 9 Apr 2015 • Aleksey Buzmakov, Elias Egho, Nicolas Jay, Sergei O. Kuznetsov, Amedeo Napoli, Chedy Raïssi
Pattern structures are used for mining complex data (such as sequences or graphs) and are based on a subsumption operation, which in our case is defined with respect to the partial order on sequences.