Search papers, labs, and topics across Lattice.
2
0
6
1
Forget PSI: Sherpa.ai's multi-party private set union enables privacy-preserving entity alignment without revealing which data points are shared, even with noisy identifiers.
Shapley-based feature attribution for multi-output models *must* decompose component-wise across outputs to satisfy standard fairness axioms, revealing a fundamental constraint on joint-output explanations.
