paper-with-me

홈 › Papers

This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation

2021-08-27 · Srishti Gautam, Marina M. -C. Höhne, Stine Hansen, Robert Jenssen, Michael Kampffmeyer

Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making strategies. As a remedy, many post-hoc explanation and self-explanatory methods have been developed to interpret the models' behavior. These methods, in addition, enable the identification of artifacts that can be learned by the model as class-relevant features. In this work, we provide a detailed case study of the self-explaining network, ProtoPNet, in the presence of a spectrum of artifacts. Accordingly, we identify the main drawbacks of ProtoPNet, especially, its coarse and spatially imprecise explanations. We address these limitations by introducing Prototypical Relevance Propagation (PRP), a novel method for generating more precise model-aware explanations. Furthermore, in order to obtain a clean dataset, we propose to use multi-view clustering strategies for segregating the artifact images using the PRP explanations, thereby suppressing the potential artifact learning in the models.

📄 PDF Abstract BibTeX arXiv:2108.12204

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition

2020-11-05 · Meike Nauta, Annemarie Jutte, Jesper Provoost, Christin Seifert

Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image "looks like" a prototype. However, perceptual si…

ClassificationGeneral Classification

Towards Few-shot Self-explaining Graph Neural Networks

2024-08-14 · Jingyu Peng, Qi Liu, Linan Yue, Zaixi Zhang 외

Recent advancements in Graph Neural Networks (GNNs) have spurred an upsurge of research dedicated to enhancing the explainability of GNNs, particularly in critical domains such as medicine. A promising approach is the se…

Self-Explaining Hate Speech Detection with Moral Rationales

2026-01-07 · Francielle Vargas, Jackson Trager, Diego Alves, Surendrabikram Thapa 외 arxiv

Hate speech detection models rely on surface-level lexical features, increasing vulnerability to spurious correlations and limiting robustness, cultural contextualization, and interpretability. We propose Supervised Mora…

Hate Speech Detection

GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection

2019-03-15 · Quoc Phong Nguyen, Kar Wai Lim, Dinil Mon Divakaran, Kian Hsiang Low 외

This paper looks into the problem of detecting network anomalies by analyzing NetFlow records. While many previous works have used statistical models and machine learning techniques in a supervised way, such solutions ha…

Anomaly Detection

Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations

2021-06-21 · Witold Oleszkiewicz, Dominika Basaj, Igor Sieradzki, Michał Górszczak 외

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approac…

Representation Learning