Distance Explainer adapts RISE-style random masking to produce attribution maps for pairwise distances in arbitrary embedding spaces, using rank-based mask selection and a two-sided mirror mode.
In: 29th ACM International Conference on Architectural Sup- port for Programming Languages and Operating Systems, Volume 2 (AS- PLOS ’24)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explainable embeddings with Distance Explainer
Distance Explainer adapts RISE-style random masking to produce attribution maps for pairwise distances in arbitrary embedding spaces, using rank-based mask selection and a two-sided mirror mode.