Session-based Recommender Systems Using Graph Convolutional Networks

General Information:

Cover Page:

Outline:

General Introduction. A. Background B. Problem Statement C. Delimitation D. Approach E. Outline Chapter 1. Session-Based Recommender Systems . 1.1. Introduction 1.2. Recommender Systems 1.3. Overview of Recommender Systems Types . 1.3.1. Content-based filtering. 1.3.2. Collaborative-filetring 1.3.3. Hybrid-filtering. 1.3.4. Knowledge-based recommender systems 1.3.5. Demographic-based filtering 1.3.6. Context-aware filtering (CARS) 1.4. Evaluation Metrics for Recommender Systems. 1.4.1. Predictive Accuracy Metrics . 1.4.2. Mean reciprocal rank (MRR) . 1.4.3. Novelty Metrics. 1.4.4. Diversity Metrics. 1.4.5. Serendipity Metrics. 1.4.6. Coverage Metrics 1.5. Experimental Settings 1.5.1. Offline Experiments 1.5.2. User Studies 1.5.3. Online evaluation. 1.6. Limitations and Challenges of Recommender Systems 1.6.1. Cold Start 1.6.2. Scalability 1.6.3. Data Sparsity 1.6.4. Synonymy 1.6.5. Shilling attacks 1.6.6. Privacy Concern 1.7. Session-based Recommender Systems 1.7.1. Overview . 1.7.2. Session and Session Properties 1.7.3. Sub-area of SBRS 1.7.4. Characteristics and Challenges. 1.8. Conclusion . Chapter 2. Graph Convolutional Networks. 2.1. Introduction 2.2. learning/” class=”tat-p” style=”color:#0073aa;font-weight:bold;”>Deep learning 2.2.1. Overview . 2.2.2. Learning processes . 2.3. Artificial Neural Networks . 2.3.1. Overview . 2.3.2. ANNs architecture 2.3.3. Activation functions 2.3.4. Feed-forward Neural Network . 2.4. Recurrent Neural Networks . 2.4.1. Overview . 2.4.2. RNNs Architecture . 2.5. Convolutional neural networks 2.5.1. Overview . 2.5.2. CNN Architecture . 2.6. Graph fundamentals. 2.6.1. Overview . 2.6.2. Graph representation . 2.6.3. Algebra representation of graphs . 2.6.4. Computational Tasks on Graphs 2.6.5. Graph applications . 2.7. Graph Neural Networks 2.7.1. Overview . 2.7.2. GNNs architecture 2.7.3. GNNs types . 2.7.4. GNNs tasks . 2.7.5. GNNs advantages and limitations 2.8. Graph Convolutional Networks 2.8.1. Main ideas. 2.8.2. Definition and principals 2.8.3. GCN architecture 2.8.4. GCN variations 2.8.5. GCN types . 2.8.6. An explanation example . 2.9. Conclusion Chapter 3. Graph Convolutional Networks for the Development of Session-based Recommender Systems 3.1. Introduction 3.2. Presentation of our GCN-based Model 3.2.1. Main idea 3.2.2. Session representation 3.2.3. GCN model 3.2.4. Recommendation step 3.3. Implementation 3.3.1. Python. 3.3.2. Libraries 3.3.3. IDE Google Collab 3.3.4. Model implementation . 3.4. Experiments and Analysis 3.4.1. Datasets. 3.4.2. Data processing. 3.4.3. Session Construction 3.4.4. Training & Testing 3.5. Evaluation Metrics 3.5.1. Baseline. 3.6. Conclusion General Conclusion A. Summary B. Direction for future research Bibliography.

Download The Thesis:

📥 تحميل الملف

For more academic sources and references, including theses and dissertations from Algerian universities, , visit our main website.