Zero-shot Concept Bottleneck Models

1. 1Identify high-level semantic concepts relevant to the task
2. 2Use pre-trained language models or knowledge graphs to learn input-to-concept mappings
3. 3Learn concept-to-label mappings using zero-shot learning techniques
4. 4Evaluate the model's performance on the target task without requiring target task training

ML researchers and engineers working on interpretable models can benefit from this approach as it reduces the need for extensive training data and resources, while also providing insights into the decision-making process of the model

💡 Zero-shot concept bottleneck models can learn to predict labels without requiring target task training, making them more efficient and interpretable

💡 Zero-shot concept bottleneck models enable interpretable neural networks without target task training!