REVIEW 7 cited by
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
abstract
Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. However, there has been little work on interpreting them, and specifically on understanding which parts of the graphs (e.g. syntactic trees or co-reference structures) contribute to a prediction. In this work, we introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. Given a trained GNN model, we learn a simple classifier that, for every edge in every layer, predicts if that edge can be dropped. We demonstrate that such a classifier can be trained in a fully differentiable fashion, employing stochastic gates and encouraging sparsity through the expected $L_0$ norm. We use our technique as an attribution method to analyze GNN models for two tasks -- question answering and semantic role labeling -- providing insights into the information flow in these models. We show that we can drop a large proportion of edges without deteriorating the performance of the model, while we can analyse the remaining edges for interpreting model predictions.
Forward citations
Cited by 7 Pith papers
-
B-cos GNNs: Faithful Explanations through Dynamic Linearity
B-cos GNNs achieve inherent explainability in graph neural networks by using linear aggregation and B-cos transforms to produce exact per-node per-feature contribution decompositions via dynamic linearity.
-
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to ...
-
Clue-Guided Money Laundering Group Discovery
Clue2Group recovers laundering groups from initial clues via local context, GNN-based risk fields, and evidence integration on AML benchmarks.
-
B-cos GNNs: Faithful Explanations through Dynamic Linearity
B-cos GNNs replace non-linear message and update functions with B-cos transforms in GNNs to enable exact per-node per-feature explanations from a single forward-backward pass while retaining competitive accuracy.
-
TACENR: Task-Agnostic Contrastive Explanations for Node Representations
TACENR introduces a contrastive-learning method that identifies the most influential attribute, proximity, and structural features in node representations in a task-agnostic manner.
-
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Benchmark study of ten GNN explainers on eight architectures and six datasets that isolates usable components and issues practical recommendations.
-
Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
SeeExplainer explains GNN predictions by decomposing graphs into granular balls and selecting substructures whose removal changes predictions, but its reported stability and fidelity advantages are largely definitiona...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.