5 papers
Concept Graph Convolutions: Message Passing in the Concept Space
Lucie Charlotte Magister, Pietro Lio
The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanation…
Subgraph Concept Networks: Concept Levels in Graph Classification
Lucie Charlotte Magister, Alexander Norcliffe, Iulia Duta +1
The reasoning process of Graph Neural Networks is complex and considered opaque, limiting trust in their predictions. To alleviate this issue, prior work has proposed concept-based…
Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust
Mohsen Abbaspour Onari, Lucie Charlotte Magister, Yaoxin Wu +10
Distal myopathy represents a genetically heterogeneous group of skeletal muscle disorders with broad clinical manifestations, posing diagnostic challenges in radiology. To address…
On the Way to LLM Personalization: Learning to Remember User Conversations
Lucie Charlotte Magister, Katherine Metcalf, Yizhe Zhang +1
Large Language Models (LLMs) have quickly become an invaluable assistant for a variety of tasks. However, their effectiveness is constrained by their ability to tailor responses to…
Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts
Shiye Su, Iulia Duta, Lucie Charlotte Magister +1
Hypergraph neural networks are a class of powerful models that leverage the message passing paradigm to learn over hypergraphs, a generalization of graphs well-suited to describing…