Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning
This work addresses the gap in causal representation learning for real-world applications by providing a more complex benchmark, though it is incremental as it builds on existing efforts in the field.
The authors tackled the problem of learning causal representations from complex visual scenes by introducing Causal Triplet, a benchmark that includes actionable counterfactual settings and interventional downstream tasks for out-of-distribution robustness, finding that models with disentangled or object-centric representations outperform distributed ones but current methods still struggle to identify latent structures.
Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work. Our code and datasets will be available at https://sites.google.com/view/causaltriplet.