MA-GIG uses VAE latent space to align Integrated Gradients paths with the data manifold for more faithful feature attributions in deep neural networks.
Not just a black box: Learning important features through propagating activation differences
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Note: This paper describes an older version of DeepLIFT. See https://arxiv.org/abs/1704.02685 for the newer version. Original abstract follows: The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Learning Important FeaTures), an efficient and effective method for computing importance scores in a neural network. DeepLIFT compares the activation of each neuron to its 'reference activation' and assigns contribution scores according to the difference. We apply DeepLIFT to models trained on natural images and genomic data, and show significant advantages over gradient-based methods.
verdicts
UNVERDICTED 6representative citing papers
An iERF-centric framework unifies local, global, and mechanistic interpretability in vision models via SRD for saliency, CAFE for concept anchoring, and ICAT for interlayer attribution.
GNNs with ontology-derived semantic loss create hierarchy-aware box embeddings of a yeast knowledge graph that raise double-knockout growth prediction R² to 0.377 and generalize to triple knockouts while identifying a validated trait association.
CAAP produces patch attributions in ViTs by direct activation patching on intermediate layers to measure causal contribution to the target class score.
LiMA reformulates attribution as submodular subset selection and uses bidirectional greedy search to identify minimal important regions, reporting 36.3% better insertion and 39.6% better deletion scores than prior methods on eight foundation models.
Heterogeneous graph neural networks with post-hoc explanations improve accuracy on six land-use indicators from mobility data and provide feature attribution and counterfactual insights aligned with commuting patterns.
citing papers explorer
-
Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution
MA-GIG uses VAE latent space to align Integrated Gradients paths with the data manifold for more faithful feature attributions in deep neural networks.
-
From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
An iERF-centric framework unifies local, global, and mechanistic interpretability in vision models via SRD for saliency, CAFE for concept anchoring, and ICAT for interlayer attribution.
-
Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction
GNNs with ontology-derived semantic loss create hierarchy-aware box embeddings of a yeast knowledge graph that raise double-knockout growth prediction R² to 0.377 and generalize to triple knockouts while identifying a validated trait association.
-
Causal Attribution via Activation Patching
CAAP produces patch attributions in ViTs by direct activation patching on intermediate layers to measure causal contribution to the target class score.
-
Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection
LiMA reformulates attribution as submodular subset selection and uses bidirectional greedy search to identify minimal important regions, reporting 36.3% better insertion and 39.6% better deletion scores than prior methods on eight foundation models.
-
Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference
Heterogeneous graph neural networks with post-hoc explanations improve accuracy on six land-use indicators from mobility data and provide feature attribution and counterfactual insights aligned with commuting patterns.