Do Concept Bottleneck Models Respect Localities?
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.
Code (1)
Similar Papers 제목 키워드 기반
An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning
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 LearningCoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes
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
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 LearningPaleoindian technological provisioning strategies in the northwestern Great Basin
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
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…