Recommender Systems (RSs) are pivotal in diverse domains such as e-commerce, music streaming, and social media.

The first part of the seminar presents a comparative analysis of key loss functions in recommender systems: Binary Cross-Entropy (BCE), Categorical Cross-Entropy (CCE), and Bayesian Personalized Ranking (BPR), which distinguish between positive items (interacted by users) and negative items. While previous studies have empirically shown that CCE outperforms BCE and BPR with the full set of negative items, we provide a theoretical explanation by proving that CCE offers the tightest lower bound on ranking metrics like Normalized Discounted Cumulative Gain (NDCG). Given that using the full set of negatives is computationally expensive, we derive bounds for these losses in negative sampling settings, establishing a probabilistic lower bound for NDCG. Our analysis shows that BPR's bound on NDCG is weaker than BCE’s, challenging the common belief that BPR is superior to BCE in recommender system training.

Beyond loss function analysis, we turn our attention to the robustness of Sequential Recommender Systems against data perturbations. Traditional similarity measures, such as Rank-Biased Overlap, prove inadequate for evaluating ranking stability in finite-length sequences. To address this, we introduce Finite Rank-Biased Overlap, a novel similarity measure tailored for practical scenarios. Through empirical analysis of item removal at different positions in temporally ordered sequences, we demonstrate that the impact on recommendation quality is highly position-dependent, with removals at the end of sequences leading to significant performance degradation.

This course provides a comprehensive overview of neural recommender systems, focusing on their foundations, state-of-the-art advancements, and practical challenges. It covers essential deep learning architectures and techniques that power modern recommender systems, exploring their role in personalizing user experiences across various domains such as e-commerce, entertainment, and social media. Key topics include sequence-based models, which capture sequential user behavior, and Transformer-based approaches, which leverage attention mechanisms for better context understanding. The course also delves into graph-based recommendation models, which model relationships between users and items in complex networks. By the end of the course, students will gain a strong understanding of neural recommender systems, their applications, and the challenges of deploying them in real-world settings.

The course is designed for graduate students and researchers with a foundational understanding of machine learning and deep learning. Familiarity with basic neural network architectures (e.g., CNNs, RNNs) is recommended.

The course will appeal to students from related areas such as natural language processing, and computer vision, and optimization, given its focus on domain-specific applications. The emphasis on ethical considerations and explainability will also interest students working on Safe, Explainable, and Trustworthy AI.

This course provides a comprehensive overview of neural recommender systems, focusing on their foundations, state-of-the-art advancements, and practical challenges. It covers essential deep learning architectures and techniques that power modern recommender systems, exploring their role in personalizing user experiences across various domains such as e-commerce, entertainment, and social media. Key topics include sequence-based models, which capture sequential user behavior, and Transformer-based approaches, which leverage attention mechanisms for better context understanding. The course also delves into graph-based recommendation models, which model relationships between users and items in complex networks. By the end of the course, students will gain a strong understanding of neural recommender systems, their applications, and the challenges of deploying them in real-world settings.

The course is designed for graduate students and researchers with a foundational understanding of machine learning and deep learning. Familiarity with basic neural network architectures (e.g., CNNs, RNNs) is recommended.

Yes, the course will appeal to students from related areas such as natural language processing, and computer vision, and optimization, given its focus on domain-specific applications. The emphasis on ethical considerations and explainability will also interest students working on Safe, Explainable, and Trustworthy AI.

This course provides a comprehensive overview of neural recommender systems, focusing on their foundations, state-of-the-art advancements, and practical challenges. It covers essential deep learning architectures and techniques that power modern recommender systems, exploring their role in personalizing user experiences across various domains such as e-commerce, entertainment, and social media. Key topics include sequence-based models, which capture sequential user behavior, and Transformer-based approaches, which leverage attention mechanisms for better context understanding. The course also delves into graph-based recommendation models, which model relationships between users and items in complex networks. By the end of the course, students will gain a strong understanding of neural recommender systems, their applications, and the challenges of deploying them in real-world settings.

The course is designed for graduate students and researchers with a foundational understanding of machine learning and deep learning. Familiarity with basic neural network architectures (e.g., CNNs, RNNs) is recommended.

Yes, the course will appeal to students from related areas such as natural language processing, and computer vision, and optimization, given its focus on domain-specific applications. The emphasis on ethical considerations and explainability will also interest students working on Safe, Explainable, and Trustworthy AI.