Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Shaobo, Tang, Hongxuan, Wang, Mingyang, Zhang, Hongrui, Liu, Xuyang, Li, Weiya, Hu, Xuming, Zhang, Linfeng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912244139294720
author Wang, Shaobo
Tang, Hongxuan
Wang, Mingyang
Zhang, Hongrui
Liu, Xuyang
Li, Weiya
Hu, Xuming
Zhang, Linfeng
author_facet Wang, Shaobo
Tang, Hongxuan
Wang, Mingyang
Zhang, Hongrui
Liu, Xuyang
Li, Weiya
Hu, Xuming
Zhang, Linfeng
contents The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, AutoGnothi, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. AutoGnothi enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that AutoGnothi offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
Wang, Shaobo
Tang, Hongxuan
Wang, Mingyang
Zhang, Hongrui
Liu, Xuyang
Li, Weiya
Hu, Xuming
Zhang, Linfeng
Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Computer Science and Game Theory
The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, AutoGnothi, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. AutoGnothi enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that AutoGnothi offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability.
title Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
topic Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Computer Science and Game Theory
url https://arxiv.org/abs/2410.21815