Assessment explanation approaches for black box models / Khaled Bouabdallah  

Public ISBD Titre : Assessment explanation approaches for black box models Type de document : texte imprimé Auteurs : Khaled Bouabdallah, Auteur ; Seddik Boudissa, Auteur ; Ahlem Drif, Directeur de thèse Année de publication : 2022 Importance : 1 vol (79 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Artificial Intelligence Explainable Artificial Intelligence Index. décimale : 004 Informatique Résumé : Machine learning models, particularly deep learning models, are frequently referred to as ”black box models” due to their enormous complexity. Because of their lack of open- ness, they are difficult to understand and trust. To address this issue and create models with results that humans can understand, a subfield of artificial intelligence (AI) known as Ex- plainable Artificial Intelligence (XAI) was created. This thesis aims to provide an in-depth examination of XAI techniques as well as propose new approaches. We propose the Dis- criminitve Attention Guided Convolutional Neural Network (DAG-CNN), which focuses on lesion regions when making diagnoses and compares similarities between cases for thorax disease classification. This approach showed promising results with competitive accuracy and more explanation in comparison to other state-of-the-art solutions. We also proposed a grey-box model based on semi-supervised methodology utilizing a self-labeling framework that combines the advantages of both black-box and white-box models. The proposed self- labeling Grey-Box shows an accurate black-box classifier for labeling the unlabeled data and a white-box surrogate classifier for building an interpretable model. Côte titre : MAI/0575 En ligne : https://drive.google.com/file/d/1Qf6_zEg10-4tItJ2LU3ek8BrGRtkZE6M/view?usp=share [...] Format de la ressource électronique : pdf Assessment explanation approaches for black box models [texte imprimé] / Khaled Bouabdallah, Auteur ; Seddik Boudissa, Auteur ; Ahlem Drif, Directeur de thèse . - 2022 . - 1 vol (79 f .) ; 29cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Artificial Intelligence Explainable Artificial Intelligence Index. décimale : 004 Informatique Résumé : Machine learning models, particularly deep learning models, are frequently referred to as ”black box models” due to their enormous complexity. Because of their lack of open- ness, they are difficult to understand and trust. To address this issue and create models with results that humans can understand, a subfield of artificial intelligence (AI) known as Ex- plainable Artificial Intelligence (XAI) was created. This thesis aims to provide an in-depth examination of XAI techniques as well as propose new approaches. We propose the Dis- criminitve Attention Guided Convolutional Neural Network (DAG-CNN), which focuses on lesion regions when making diagnoses and compares similarities between cases for thorax disease classification. This approach showed promising results with competitive accuracy and more explanation in comparison to other state-of-the-art solutions. We also proposed a grey-box model based on semi-supervised methodology utilizing a self-labeling framework that combines the advantages of both black-box and white-box models. The proposed self- labeling Grey-Box shows an accurate black-box classifier for labeling the unlabeled data and a white-box surrogate classifier for building an interpretable model. Côte titre : MAI/0575 En ligne : https://drive.google.com/file/d/1Qf6_zEg10-4tItJ2LU3ek8BrGRtkZE6M/view?usp=share [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0575	MAI/0575	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

A Deep Learning Model For Collaborative Filtering / Ferkous, Mohamed Laid  

Public ISBD Titre : A Deep Learning Model For Collaborative Filtering Type de document : texte imprimé Auteurs : Ferkous, Mohamed Laid, Auteur ; Ahlem Drif, Directeur de thèse Editeur : Setif:UFA Année de publication : 2021 Importance : 1 vol (83 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems Mutual Influence Graph Attention Network Index. décimale : 004 - Informatique Résumé : Recommender systems have become an integral part of e-commerce sites and other platforms such as social networking, movie/-music rendering websites. Network representation learning have been used as a successful approaches to build efficient recommender systems. However, learning the mutual influence generated by the contributions of each node in the network is a challenging issue. In fact, the mutual influence carries collaborative signals on user decisions helping to account for complex user-item interactions. For this purpose, in this master thesis, we propose Multual Intercation Graph Attention Network ‘MIGAN” which is a new algorithm based on a the self-supervised representation learning on large scale bipartite graph (BGNN). Experiments on real-world datasets demonstrate that the proposed Graph learning method can achieve more accurate predictions and higher recommendation efficiency. Côte titre : MAI/0522 En ligne : https://drive.google.com/file/d/1mGYDn5WsQu4tz8wXwWqFf3RXOFw_iyJV/view?usp=shari [...] Format de la ressource électronique : pdf A Deep Learning Model For Collaborative Filtering [texte imprimé] / Ferkous, Mohamed Laid, Auteur ; Ahlem Drif, Directeur de thèse . - [S.l.] : Setif:UFA, 2021 . - 1 vol (83 f .) ; 29 cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems Mutual Influence Graph Attention Network Index. décimale : 004 - Informatique Résumé : Recommender systems have become an integral part of e-commerce sites and other platforms such as social networking, movie/-music rendering websites. Network representation learning have been used as a successful approaches to build efficient recommender systems. However, learning the mutual influence generated by the contributions of each node in the network is a challenging issue. In fact, the mutual influence carries collaborative signals on user decisions helping to account for complex user-item interactions. For this purpose, in this master thesis, we propose Multual Intercation Graph Attention Network ‘MIGAN” which is a new algorithm based on a the self-supervised representation learning on large scale bipartite graph (BGNN). Experiments on real-world datasets demonstrate that the proposed Graph learning method can achieve more accurate predictions and higher recommendation efficiency. Côte titre : MAI/0522 En ligne : https://drive.google.com/file/d/1mGYDn5WsQu4tz8wXwWqFf3RXOFw_iyJV/view?usp=shari [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0522	MAI/0522	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

Recommender system based on Graph learning model / Makhlouf Tabti

Public ISBD Titre : Recommender system based on Graph learning model Type de document : texte imprimé Auteurs : Makhlouf Tabti, Auteur ; Mohamed Amine Tamhachet ; Ahlem Drif, Directeur de thèse Editeur : Setif:UFA Année de publication : 2024 Importance : 1 vol (50 f .) Format : 29 cm Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems (RS) Hybrid recommender system (HRS) Collaborative filtering(CF) Graph Neural Networks (GNN) Season Filtering(SF) Graph Convolutional Networks (GCN) Index. décimale : 004 - Informatique Résumé : The variability of user preferences over time poses a major challenge for recommender systems. Consequently, several works have focused on time-sensitive recommender systems, leading to a plethora of studies in this domain. In this master thesis, we target the temporal dimension when providing user recommendations, integrating and leveraging temporal data to enhance the recommendation process. For this purpose, we develop a temporal recommender model incorporating seasonality filtring to the famous graph-based model LightGCN by tweaking its recommendation mechanism to overcome the difficulties posed by item-wise cold start. The developed framework contains two modules: 1-) A Supervised LightGCN, 2-) a Season filtering component. The empirical study on real-world datasets proves that the proposed recommender system significantly outperforms the state-of-the-art methods in terms of recommendation performance with 0.90 of mean average precision. Note de contenu : Sommaire General Introduction 1 1 Machine Learning - Theoretical Background 3 1.1 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.2 Uses and Applications . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.3 Types of Machine Learning Models . . . . . . . . . . . . . . . . 5 1.1.3.1 Supervised Learning . . . . . . . . . . . . . . . . . . . 5 1.1.3.2 Unsupervised Learning . . . . . . . . . . . . . . . . . . 6 1.1.3.3 Reinforcement Learning . . . . . . . . . . . . . . . . . 6 1.1.3.4 Hybrid Learning . . . . . . . . . . . . . . . . . . . . . 6 1.2 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.2 From Biological Neurons to the Perceptron . . . . . . . . . . . . 7 1.2.3 Types of Artificial Neural Networks . . . . . . . . . . . . . . . . 8 1.2.3.1 Feed-Forward Neural Networks . . . . . . . . . . . . . 9 1.3 Graph Neural Networks (GNN) . . . . . . . . . . . . . . . . . . . . . . 12 1.3.1 Introduction to Graphs . . . . . . . . . . . . . . . . . . . . . . . 12 1.3.2 Why Graphs? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 1.3.3 Types of tasks on Graph Neural Networks . . . . . . . . . . . . 14 1.3.4 Node Embeddings . . . . . . . . . . . . . . . . . . . . . . . . . . 15 1.3.5 Edge Representation: . . . . . . . . . . . . . . . . . . . . . . . . 17 1.3.6 Types of graph neural networks : . . . . . . . . . . . . . . . . . 17 1.3.6.1 Graph Convolutional Networks (GCNs): . . . . . . . . 17 1.3.6.2 Graph Attention Networks (GATs): . . . . . . . . . . . 17 1.3.6.3 GraphSAGE: . . . . . . . . . . . . . . . . . . . . . . . 18 1.3.7 Message Passing and Aggregation: . . . . . . . . . . . . . . . . . 18 1.3.7.1 The message passing paradigm in GNNs: . . . . . . . . 18 1.3.7.2 Aggregation functions: . . . . . . . . . . . . . . . . . . 18 1.3.7.3 Neighborhood aggregation strategies: . . . . . . . . . . 18 1.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 2 Survey on Recommendation Methods 20 2.1 Introduction to Recommender Systems . . . . . . . . . . . . . . . . . . 21 2.1.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.1.2 The User-Item Interaction Matrix . . . . . . . . . . . . . . . . . 21 2.2 Basic architectures of recommender systems . . . . . . . . . . . . . . . 22 2.2.1 Content-Based Recommendation . . . . . . . . . . . . . . . . . 22 2.2.2 Collaborative filtering recommendation . . . . . . . . . . . . . . 23 2.2.3 Knowledge-based recommender systems . . . . . . . . . . . . . . 23 2.2.4 Hybrid Recommender Systems . . . . . . . . . . . . . . . . . . . 24 2.3 Temporal graph neural network . . . . . . . . . . . . . . . . . . . . . . 24 2.3.1 Temporal graph neural network for recommender systems . . . . 24 2.3.2 Graph Neural Network for recommender model . . . . . . . . . 24 2.3.3 Notations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 2.3.4 Graph node representation . . . . . . . . . . . . . . . . . . . . . 25 2.4 Graph Neural Network architectures . . . . . . . . . . . . . . . . . . . 26 2.4.1 Graph Convolution Network (GCN) . . . . . . . . . . . . . . . . 26 2.4.2 Neural Graph Collaborative Filtering (NGCF) . . . . . . . . . . 27 2.4.3 LightGCN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 2.4.4 Disentangled Graph Collaborative Filtering (DGCF) . . . . . . 29 2.4.5 Interest-aware Message-Passing GCN . . . . . . . . . . . . . . . 30 2.4.6 Hamming Spatial Graph Convolution Neural Network . . . . . . 30 2.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 3 LightGCN with Season Filtering for recommender system 32 3.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 3.2 Our proposed framework . . . . . . . . . . . . . . . . . . . . . . . . . . 33 3.2.1 LightGCN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 3.2.2 Seasonality Filtering component . . . . . . . . . . . . . . . . . . 35 3.2.3 Generating Recommendations . . . . . . . . . . . . . . . . . . . 36 3.3 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 4 Experimenting with The Proposed Approach 38 4.1 Environment and Tools . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 4.1.1 Hardware Development-Testing Environment . . . . . . . . . . . 38 4.1.2 Software Environment and Tools . . . . . . . . . . . . . . . . . 39 4.2 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 4.2.1 The Amazon Dataset . . . . . . . . . . . . . . . . . . . . . . . . 41 4.3 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 4.3.1 Mean Average Precision: . . . . . . . . . . . . . . . . . . . . . . 41 4.4 Hyper-parameters and functions . . . . . . . . . . . . . . . . . . . . . 42 4.5 Performance comparison with the baselines . . . . . . . . . . . . . . . . 43 4.5.1 Baselines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 4.6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 Côte titre : MAI/0865 Recommender system based on Graph learning model [texte imprimé] / Makhlouf Tabti, Auteur ; Mohamed Amine Tamhachet ; Ahlem Drif, Directeur de thèse . - [S.l.] : Setif:UFA, 2024 . - 1 vol (50 f .) ; 29 cm. Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems (RS) Hybrid recommender system (HRS) Collaborative filtering(CF) Graph Neural Networks (GNN) Season Filtering(SF) Graph Convolutional Networks (GCN) Index. décimale : 004 - Informatique Résumé : The variability of user preferences over time poses a major challenge for recommender systems. Consequently, several works have focused on time-sensitive recommender systems, leading to a plethora of studies in this domain. In this master thesis, we target the temporal dimension when providing user recommendations, integrating and leveraging temporal data to enhance the recommendation process. For this purpose, we develop a temporal recommender model incorporating seasonality filtring to the famous graph-based model LightGCN by tweaking its recommendation mechanism to overcome the difficulties posed by item-wise cold start. The developed framework contains two modules: 1-) A Supervised LightGCN, 2-) a Season filtering component. The empirical study on real-world datasets proves that the proposed recommender system significantly outperforms the state-of-the-art methods in terms of recommendation performance with 0.90 of mean average precision. Note de contenu : Sommaire General Introduction 1 1 Machine Learning - Theoretical Background 3 1.1 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.2 Uses and Applications . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.3 Types of Machine Learning Models . . . . . . . . . . . . . . . . 5 1.1.3.1 Supervised Learning . . . . . . . . . . . . . . . . . . . 5 1.1.3.2 Unsupervised Learning . . . . . . . . . . . . . . . . . . 6 1.1.3.3 Reinforcement Learning . . . . . . . . . . . . . . . . . 6 1.1.3.4 Hybrid Learning . . . . . . . . . . . . . . . . . . . . . 6 1.2 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.2 From Biological Neurons to the Perceptron . . . . . . . . . . . . 7 1.2.3 Types of Artificial Neural Networks . . . . . . . . . . . . . . . . 8 1.2.3.1 Feed-Forward Neural Networks . . . . . . . . . . . . . 9 1.3 Graph Neural Networks (GNN) . . . . . . . . . . . . . . . . . . . . . . 12 1.3.1 Introduction to Graphs . . . . . . . . . . . . . . . . . . . . . . . 12 1.3.2 Why Graphs? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 1.3.3 Types of tasks on Graph Neural Networks . . . . . . . . . . . . 14 1.3.4 Node Embeddings . . . . . . . . . . . . . . . . . . . . . . . . . . 15 1.3.5 Edge Representation: . . . . . . . . . . . . . . . . . . . . . . . . 17 1.3.6 Types of graph neural networks : . . . . . . . . . . . . . . . . . 17 1.3.6.1 Graph Convolutional Networks (GCNs): . . . . . . . . 17 1.3.6.2 Graph Attention Networks (GATs): . . . . . . . . . . . 17 1.3.6.3 GraphSAGE: . . . . . . . . . . . . . . . . . . . . . . . 18 1.3.7 Message Passing and Aggregation: . . . . . . . . . . . . . . . . . 18 1.3.7.1 The message passing paradigm in GNNs: . . . . . . . . 18 1.3.7.2 Aggregation functions: . . . . . . . . . . . . . . . . . . 18 1.3.7.3 Neighborhood aggregation strategies: . . . . . . . . . . 18 1.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 2 Survey on Recommendation Methods 20 2.1 Introduction to Recommender Systems . . . . . . . . . . . . . . . . . . 21 2.1.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.1.2 The User-Item Interaction Matrix . . . . . . . . . . . . . . . . . 21 2.2 Basic architectures of recommender systems . . . . . . . . . . . . . . . 22 2.2.1 Content-Based Recommendation . . . . . . . . . . . . . . . . . 22 2.2.2 Collaborative filtering recommendation . . . . . . . . . . . . . . 23 2.2.3 Knowledge-based recommender systems . . . . . . . . . . . . . . 23 2.2.4 Hybrid Recommender Systems . . . . . . . . . . . . . . . . . . . 24 2.3 Temporal graph neural network . . . . . . . . . . . . . . . . . . . . . . 24 2.3.1 Temporal graph neural network for recommender systems . . . . 24 2.3.2 Graph Neural Network for recommender model . . . . . . . . . 24 2.3.3 Notations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 2.3.4 Graph node representation . . . . . . . . . . . . . . . . . . . . . 25 2.4 Graph Neural Network architectures . . . . . . . . . . . . . . . . . . . 26 2.4.1 Graph Convolution Network (GCN) . . . . . . . . . . . . . . . . 26 2.4.2 Neural Graph Collaborative Filtering (NGCF) . . . . . . . . . . 27 2.4.3 LightGCN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 2.4.4 Disentangled Graph Collaborative Filtering (DGCF) . . . . . . 29 2.4.5 Interest-aware Message-Passing GCN . . . . . . . . . . . . . . . 30 2.4.6 Hamming Spatial Graph Convolution Neural Network . . . . . . 30 2.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 3 LightGCN with Season Filtering for recommender system 32 3.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 3.2 Our proposed framework . . . . . . . . . . . . . . . . . . . . . . . . . . 33 3.2.1 LightGCN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 3.2.2 Seasonality Filtering component . . . . . . . . . . . . . . . . . . 35 3.2.3 Generating Recommendations . . . . . . . . . . . . . . . . . . . 36 3.3 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 4 Experimenting with The Proposed Approach 38 4.1 Environment and Tools . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 4.1.1 Hardware Development-Testing Environment . . . . . . . . . . . 38 4.1.2 Software Environment and Tools . . . . . . . . . . . . . . . . . 39 4.2 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 4.2.1 The Amazon Dataset . . . . . . . . . . . . . . . . . . . . . . . . 41 4.3 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 4.3.1 Mean Average Precision: . . . . . . . . . . . . . . . . . . . . . . 41 4.4 Hyper-parameters and functions . . . . . . . . . . . . . . . . . . . . . 42 4.5 Performance comparison with the baselines . . . . . . . . . . . . . . . . 43 4.5.1 Baselines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 4.6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 Côte titre : MAI/0865

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0865	MAI/0865	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

---

1 (1 - 3 / 3)