Structural Causality-based Generalizable Concept Discovery Models
This work addresses the need for flexible and generalizable concept discovery in explainable AI, though it appears incremental as it builds on existing disentanglement and causal modeling techniques.
The paper tackles the problem of learning task-specific concepts for explainable deep neural networks by proposing a method that first learns independent generative factors using a VAE and then uses a structural causal model to derive concepts from these factors, demonstrating successful concept learning on D-sprites and Shapes3D datasets.
The rising need for explainable deep neural network architectures has utilized semantic concepts as explainable units. Several approaches utilizing disentangled representation learning estimate the generative factors and utilize them as concepts for explaining DNNs. However, even though the generative factors for a dataset remain fixed, concepts are not fixed entities and vary based on downstream tasks. In this paper, we propose a disentanglement mechanism utilizing a variational autoencoder (VAE) for learning mutually independent generative factors for a given dataset and subsequently learning task-specific concepts using a structural causal model (SCM). Our method assumes generative factors and concepts to form a bipartite graph, with directed causal edges from generative factors to concepts. Experiments are conducted on datasets with known generative factors: D-sprites and Shapes3D. On specific downstream tasks, our proposed method successfully learns task-specific concepts which are explained well by the causal edges from the generative factors. Lastly, separate from current causal concept discovery methods, our methodology is generalizable to an arbitrary number of concepts and flexible to any downstream tasks.