PT Unknown
AU Anguelos Nicolaou
   Sounak Dey
   V.Christlein
   A.Maier
   Dimosthenis Karatzas
TI Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings
BT International Workshop on Reproducible Research in Pattern Recognition
PY 2018
BP 71
EP 82
VL 11455
AB Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits.
ER