Grégoire Montavon

Unlock superior classification performance by encoding graph-like relationships between classes, sidestepping the limitations of traditional structure-agnostic loss functions.

Exponential complexity in GNN explainability is no longer a barrier: this work achieves linear-time subgraph attribution via message passing.

Observed sample displacements can be integrated into optimal transport to carve expressways through the input space, leading to more reliable modeling of distribution shifts.

Don't waste compute on unreliable explanations: epistemic uncertainty can predict when XAI methods will fail, allowing you to gate their use.