Salvato in:
Dettagli Bibliografici
Autori principali: You, Weiqiu, Zeng, Siqi, Tsai, Yao-Hung Hubert, Yamada, Makoto, Zhao, Han
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.18810
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912663138729984
author You, Weiqiu
Zeng, Siqi
Tsai, Yao-Hung Hubert
Yamada, Makoto
Zhao, Han
author_facet You, Weiqiu
Zeng, Siqi
Tsai, Yao-Hung Hubert
Yamada, Makoto
Zhao, Han
contents Leave-One-Out (LOO) provides an intuitive measure of feature importance but is computationally prohibitive. While Layer-Wise Relevance Propagation (LRP) offers a potentially efficient alternative, its axiomatic soundness in modern Transformers remains largely under-examined. In this work, we first show that the bilinear propagation rules used in recent advances of AttnLRP violate the implementation invariance axiom. We prove this analytically and confirm it empirically in linear attention layers. Second, we also revisit CP-LRP as a diagnostic baseline and find that bypassing relevance propagation through the softmax layer -- backpropagating relevance only through the value matrices -- significantly improves alignment with LOO, particularly in middle-to-late Transformer layers. Overall, our results suggest that (i) bilinear factorization sensitivity and (ii) softmax propagation error potentially jointly undermine LRP's ability to approximate LOO in Transformers.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18810
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When LRP Diverges from Leave-One-Out in Transformers
You, Weiqiu
Zeng, Siqi
Tsai, Yao-Hung Hubert
Yamada, Makoto
Zhao, Han
Machine Learning
Leave-One-Out (LOO) provides an intuitive measure of feature importance but is computationally prohibitive. While Layer-Wise Relevance Propagation (LRP) offers a potentially efficient alternative, its axiomatic soundness in modern Transformers remains largely under-examined. In this work, we first show that the bilinear propagation rules used in recent advances of AttnLRP violate the implementation invariance axiom. We prove this analytically and confirm it empirically in linear attention layers. Second, we also revisit CP-LRP as a diagnostic baseline and find that bypassing relevance propagation through the softmax layer -- backpropagating relevance only through the value matrices -- significantly improves alignment with LOO, particularly in middle-to-late Transformer layers. Overall, our results suggest that (i) bilinear factorization sensitivity and (ii) softmax propagation error potentially jointly undermine LRP's ability to approximate LOO in Transformers.
title When LRP Diverges from Leave-One-Out in Transformers
topic Machine Learning
url https://arxiv.org/abs/2510.18810