Core Concepts
Graph Convolutional Networks bieten eine effektive Methode zur Depressionserkennung in transkribierten klinischen Interviews.
Stats
"Results show that our approach consistently outperforms the vanilla GCN model as well as previously reported results, achieving an F1=0.84 on both datasets."
"Loss is computed by means of the cross-entropy function between Zi and Yi, ∀i ∈ Vtr docs."
"For each model, we also evaluated two versions, one enabling fine tuning of the base model and another not fine tuning the base model as part of the training process."
Quotes
"The proposed method aims to mitigate the limiting assumptions of locality and the equal importance of self-connections vs. edges to neighboring nodes in GCNs."
"Our best configurations require orders of magnitude fewer trainable parameters than transformer-based models."