Search papers, labs, and topics across Lattice.
Email:
5
0
6
AI malfunctions, like Clever Hans effects, can be directly traced to specific artifact patterns in the input data using a model-agnostic dictionary of interpretable concepts.
A new attribution method reveals the full spectrum of information flow in ETGNNs, enhancing explainability beyond traditional event-related embeddings.
Symb-xMIL transforms MIL interpretability by revealing the hidden logical rules that govern model predictions, exposing decision patterns that traditional heatmaps miss.
Exponential complexity in GNN explainability is no longer a barrier: this work achieves linear-time subgraph attribution via message passing.
Attention heatmaps in MIL models for histopathology are often misleading, and simpler methods like perturbation or LRP provide more faithful explanations.
