- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes Label-Agnostic Attribution for Interpretability (LAAI). It explains a symmetric objective, KL divergence from a uniform distribution to the classifier’s output probabilities. Sampled classes guide input exploration. Gradients of the shared objective are accumulated using displacements from the original image. Experiments compare attribution rankings through insertion, deletion, and distributional metrics. The main CNN results show stronger insertion performance, with weaker deletion performance than some baselines.
Critical strengths
-
The explanation target is clear and potentially useful. A shared, class-symmetric objective offers a complementary explanation when users have not selected a class to explain.
-
The main insertion results are promising. LAAI achieves the highest mean insertion scores across all six CNN–confidence settings in Tables 1–3. The paper also explicitly reports its deletion trade-offs and theoretical limitations.
Critical weaknesses
-
The core results are unclear. I understand that the exploration applies another softmax when the model already outputs probabilities. And I am confused why each example uses the entire batch target vector rather than its own target. Moreover, appendix C reports a missing evaluation dependency and module error which are unsolved. The paper does not identify a complete runnable configuration for Tables 1–3. These issues leave the main empirical claims insufficiently supported.
-
The algorithmic contribution is not isolated. The comparisons change both the explanation target and the attribution procedure. The paper lacks direct-gradient and Integrated Gradients baselines for the same KL objective. The added value of the proposed exploration and accumulation is therefore unclear.
Questions for authors
-
Which exact runnable configuration produced Tables 1–3?
-
What does the proposed procedure add over direct gradients or Integrated Gradients of the same KL objective?
3 comments
We sincerely thank the reviewer for their valuable feedback. We hope that our responses have addressed your concerns. As the rebuttal period is coming to an end, we would be happy to further discuss any remaining questions or concerns. If our responses have resolved your concerns, we would greatly appreciate it if you could reconsider your assessment of our paper in light of our clarifications.
Thank you for the rebuttal and the additional IG800 experiments. I appreciate these improvements, but three concerns remain
- Why does the exploration apply softmax again to probability outputs? Is this consistent with the KL objective in Eq. 3?
- Why does each sample use the entire batch target vector instead of its own target? Does this affect attribution consistency across different batches?
- Could you separately evaluate the contributions of class-guided exploration and displacement-weighted accumulation?
W1 / Q1: Exact configuration behind Tables 1–3.
The experiments evaluate pretrained Inception-v3, ResNet-50, and VGG16 models provided by torchvision on a fixed set of 1,000 images. Inputs have a resolution of 224×224 and use ImageNet normalization, with all models in evaluation mode. Attribution settings are shared across models: M=20 explorations, T=20 iterations per exploration, perturbation radius ϵ=0.05, and a batch size of 64.
We have provided the complete evaluation entry point and required dependencies; see Appendix C.2.
W2 / Q2: Added value over direct gradients or IG of the same KL objective.
LAAI adds class-guided exploration and displacement-weighted accumulation beyond the choice of a KL objective. Direct gradients use the local derivative at the original image; IG integrates along the straight path from a black reference image to the input. LAAI explores directions guided by sampled classes, evaluates the shared KL gradient at the explored locations, and accumulates attribution weighted by displacement from the original image (Section 3.3). Section 3.4 further analyzes the distinction between this accumulation and path integration.
The added value of exploration and accumulation is demonstrated by comparisons with the same objective and gradient budget. With the same KL objective and 800 gradient evaluations per attribution run, LAAI achieves significantly higher insertion scores than IG800 on all three models, demonstrating more effective ranking of features that support recovery of the original prediction.
The table reports LAAI minus IG800 with adjusted confidence intervals; higher ΔINS and lower ΔDEL are better.