paper-with-me

홈 › Papers

Do Concept Bottleneck Models Respect Localities?

2024-01-02 · Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik

Concept-based methods explain model predictions using human-understandable concepts. These models require accurate concept predictors, yet the faithfulness of existing concept predictors to their underlying concepts is unclear. In this paper, we investigate the faithfulness of Concept Bottleneck Models (CBMs), a popular family of concept-based architectures, by looking at whether they respect "localities" in datasets. Localities involve using only relevant features when predicting a concept's value. When localities are not considered, concepts may be predicted based on spuriously correlated features, degrading performance and robustness. This work examines how CBM predictions change when perturbing model inputs, and reveals that CBMs may not capture localities, even when independent concepts are localised to non-overlapping feature subsets. Our empirical and theoretical results demonstrate that datasets with correlated concepts may lead to accurate but uninterpretable models that fail to learn localities. Overall, we find that CBM interpretability is fragile, as CBMs occasionally rely upon spurious features, necessitating further research into the robustness of concept predictors.

📄 PDF Abstract BibTeX arXiv:2401.01259

Code (1)

naveenr414/Spurious-Concepts 공식 구현 pytorch

Similar Papers 제목 키워드 기반

An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning

2021-11-03 · Yun Li, Zhe Liu, Lina Yao, Xianzhi Wang 외

Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations. A promising strategy is to learn a global-local representation that incorporates global infor…

Generalized Zero-Shot LearningZero-Shot Learning

CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes

2025-07-11 · Sangwon Kim, Kyoungoh Lee, Jeyoun Dong, Kwang-Ju Kim arxiv

Generative concept bottleneck models aim to enable interpretable generation by routing synthesis through explicit, user-facing concepts. In practice, prior approaches often rely on non-explicit bottleneck representations…

Harnessing Rich Multi-Modal Data for Spatial-Temporal Homophily-Embedded Graph Learning Across Domains and Localities

2025-12-11 · Takuya Kurihana, Xiaojian Zhang, Wing Yee Au, Hon Yung Wong arxiv

Modern cities are increasingly reliant on data-driven insights to support decision making in areas such as transportation, public safety and environmental impact. However, city-level data often exists in heterogeneous fo…

Decision MakingGraph Learning

Paleoindian technological provisioning strategies in the northwestern Great Basin

2013-12-01 · 12/01 2013 12 · Geoffrey M.Smith, Emily S.Middleton, Peter A.Carey

Great Basin populations during the Pleistocene–Holocene Transition (PHT) are often characterized as being mobile and focused on wetlands; however, the factors that influenced where Paleoindians selected residential camps…

Commodity Booms, Local State Capacity, and Development

2024-11-14 · Dafne Murillo, Sebastian Sardon

State capacity may shape whether natural resources generate prosperity, as it determines if windfalls are effectively turned into useful projects or wasted. We test this hypothesis studying the 2004-2011 mining boom in P…