ARTFEED — Contemporary Art Intelligence

Detecting Atypical Clients in Federated Learning via Representation-Level Divergence

other · 2026-05-23

A new research paper proposes a lightweight geometric signal to detect atypical clients in federated learning by measuring how local training alters the activation-induced partition of the input space on a shared probe set. This method yields a permutation-invariant, interpretable metric of client-global divergence that captures differences in data processing, addressing challenges from heterogeneous data, distributional shifts, and anomalous inputs.

Key facts

  • arXiv:2605.22266v1
  • Announce Type: cross
  • Proposes a lightweight geometric signal
  • Quantifies functional deviation of a client with respect to the global model
  • Measures how local training alters activation-induced partition of input space
  • Evaluated on a shared probe set
  • Yields permutation-invariant, interpretable metric
  • Captures differences in how data is processed by the model

Entities

Sources