Research map / Probabilistic and scientific modeling / Causal discovery
Learning Counterfactually Decoupled Attention for Open-World Model Attribution
Yu Zheng, Boyang Gong, Fanye Kong, Yueqi Duan, Bingyao Yu, Wenzhao Zheng, Lei Chen, Jiwen Lu, Jie Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add factual attention via Causal Expert convolution to CPL (ablation) | CPL · OW-DFA Protocol 1 novel | ARI: 65.71 -> 70.34 | Improved |
| add learned counterfactual attention (ablation) | CPL + CDAL · OW-DFA Protocol 1 novel | ARI: 70.34 -> 73.54 | Improved |
| add causal attention augmentation (enhanced attention) (ablation) | CPL + CDAL · OW-DFA Protocol 1 novel | ARI: 73.54 -> 76.98 | Improved |
| add causal loss (ablation) | CPL + CDAL · OW-DFA Protocol 1 novel | ARI: 68.94 -> 71.75 | Improved |
| add decorrelation loss (ablation) | CPL + CDAL · OW-DFA Protocol 1 novel | ARI: 71.75 -> 75.08 | Improved |
| add attention diversification loss L_aug (ablation) | CPL + CDAL · OW-DFA Protocol 1 novel | ARI: 75.08 -> 76.98 | Improved |
| use 4 causal experts instead of 2, 3, 5 or 6 (ablation) | CDAL · OW-DFA Protocol 1 novel | ARI: 72.57 (N=2) -> 76.98 (N=4) -> 72.00 (N=6) | Mixed |
| replace random counterfactual attention with learned CE-Conv counterfactual attention (ablation) | CPL + CDAL · OW-DFA Protocol 1 novel | ARI: 73.54 -> 76.98 | Improved |
| add vanilla attention to CPL without CDAL (ablation) | CPL · OW-DFA Protocol 1 novel | ARI: 65.71 -> 58.81 | Hurt |
| plug CDAL into CPL | CPL · OW-DFA Protocol 1 novel | ARI: 65.71 -> 76.98 | Improved |
| plug CDAL into POSE for GAN discovery | POSE · OSMA Unseen All | purity: 41.04 -> 48.93 | Improved |
| plug CDAL into ORCA | ORCA · OW-DFA Protocol 2 novel | ARI: 49.15 -> 50.42 | Mixed |
Closest papers by meaning
- Rethinking Visual Counterfactual Explanations Through Region Constraint (ICLR 2025 · similarity 0.85)
- Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition (CVPR 2025 · similarity 0.85)
- Counterfactual Generative Modeling with Variational Causal Inference (ICLR 2025 · similarity 0.85)
- Real-Time Visual Attribution Streaming in Thinking Model (ICML 2026 · similarity 0.84)
- V-CECE: Visual Counterfactual Explanations via Conceptual Edits (NeurIPS 2025 · similarity 0.84)
- Counterfactual Maps: What They Are and How to Find Them (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
