3 accepted papers
Transformer-based models have achieved state-of-the-art performance in document classification but struggle with long-text processing due to the quadratic computational complexity in the self-attention module. Existing solutions, such as sparse attention, hierarchical models, and key sentence extrac…
Learning to predict rare medical events is difficult due to the inherent lack of signal in highly imbalanced datasets. Yet, oftentimes we also have access to surrogate or related outcomes that we believe share etiology or underlying risk factors with the event of interest. In this work, we propose t…
Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative solution by constructing infinite tree-structured PGMs that correspond exactly to neural networks. Our research reveals…