Process-Guided Concept Bottleneck Model
By: Reza M. Asiyabi , SEOSAW Partnership , Steven Hancock and more
Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their dependence on complete concept labels limits applicability in scientific domains where supervision is sparse but processes are well defined. To address this, we propose the Process-Guided Concept Bottleneck Model (PG-CBM), an extension of CBMs which constrains learning to follow domain-defined causal mechanisms through biophysically meaningful intermediate concepts. Using above ground biomass density estimation from Earth Observation data as a case study, we show that PG-CBM reduces error and bias compared to multiple benchmarks, whilst leveraging multi-source heterogeneous training data and producing interpretable intermediate outputs. Beyond improved accuracy, PG-CBM enhances transparency, enables detection of spurious learning, and provides scientific insights, representing a step toward more trustworthy AI systems in scientific applications.
Similar Papers
Controllable Concept Bottleneck Models
Machine Learning (CS)
Makes smart models easily fixable and updatable.
Graph Concept Bottleneck Models
Machine Learning (CS)
Shows how ideas connect to understand pictures.
Partially Shared Concept Bottleneck Models
CV and Pattern Recognition
Makes AI explain its decisions clearly and accurately.