EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
This work addresses the need for more reliable and interpretable AI systems by enhancing CBMs, offering an incremental improvement for applications requiring human-understandable concepts.
The paper tackles the problem of inaccuracies in concept bottleneck models (CBMs) due to deterministic concept encoding and inconsistent concepts, proposing EQ-CBM, which uses probabilistic encoding with energy-based models and quantized vectors to improve reliability and accuracy, outperforming state-of-the-art methods in concept and task accuracy on benchmark datasets.
The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance interpretability. However, existing CBMs face challenges due to deterministic concept encoding and reliance on inconsistent concepts, leading to inaccuracies. We propose EQ-CBM, a novel framework that enhances CBMs through probabilistic concept encoding using energy-based models (EBMs) with quantized concept activation vectors (qCAVs). EQ-CBM effectively captures uncertainties, thereby improving prediction reliability and accuracy. By employing qCAVs, our method selects homogeneous vectors during concept encoding, enabling more decisive task performance and facilitating higher levels of human intervention. Empirical results using benchmark datasets demonstrate that our approach outperforms the state-of-the-art in both concept and task accuracy.