5 papers
MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning
Ahmad Mousavi, Majid Alikhani, Yeon-Chang Lee +2
Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse interaction data with content features. Yet current architectures face two bottlenecks…
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
Katarzyna Filus, Kamil Faber, Roberto Corizzo +1
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catas…
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Maxwell Miller-Golub, Collin Coil, Kamil Faber +4
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencie…
E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection
Ahmad Mousavi, Yeganeh Abdollahinejad, Roberto Corizzo +2
Detecting multimodal misinformation on social media remains challenging due to inconsistencies between modalities, changes in temporal patterns, and substantial class imbalance. Ma…
Pulling Back the Curtain on Deep Networks
Maciej Satkiewicz, Roberto Corizzo, Marcin Pietroń
In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or gradient ascen…