Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking

• URL: http://arxiv.org/abs/2010.00577v3
• Date: Mon, 3 Oct 2022 10:22:35 GMT
• Title: Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
• Authors: Michael Sejr Schlichtkrull, Nicola De Cao, Ivan Titov
• Abstract summary: Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
• Score: 63.49779304362376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Improving the interpretability of GNN predictions through conformal-based graph sparsification [9.550589670316523]
  Graph Neural Networks (GNNs) have achieved state-of-the-art performance in solving graph classification tasks. We propose a GNN emphtraining approach that finds the most predictive subgraph by removing edges and/or nodes. We rely on reinforcement learning to solve the resulting bi-level optimization with a reward function based on conformal predictions.
  arXiv  Detail & Related papers  (2024-04-18T17:34:47Z)
• Text Representation Enrichment Utilizing Graph based Approaches: Stock Market Technical Analysis Case Study [0.0]
  We propose a transductive hybrid approach composed of an unsupervised node representation learning model followed by a node classification/edge prediction model. The proposed model is developed to classify stock market technical analysis reports, which to our knowledge is the first work in this domain.
  arXiv  Detail & Related papers  (2022-11-29T11:26:08Z)
• Discovering Invariant Rationales for Graph Neural Networks [104.61908788639052]
  Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features. We propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs.
  arXiv  Detail & Related papers  (2022-01-30T16:43:40Z)
• A Meta-Learning Approach for Training Explainable Graph Neural Networks [10.11960004698409]
  We propose a meta-learning framework for improving the level of explainability of a GNN directly at training time. Our framework jointly trains a model to solve the original task, e.g., node classification, and to provide easily processable outputs for downstream algorithms. Our model-agnostic approach can improve the explanations produced for different GNN architectures and use any instance-based explainer to drive this process.
  arXiv  Detail & Related papers  (2021-09-20T11:09:10Z)
• Learnt Sparsification for Interpretable Graph Neural Networks [5.527927312898106]
  We propose a novel method called Kedge for explicitly sparsifying the underlying graph by removing unnecessary neighbors. Kedge learns edge masks in a modular fashion trained with any GNN allowing for gradient based optimization. We show that Kedge effectively counters the over-smoothing phenomena in deep GNNs by maintaining good task performance with increasing GNN layers.
  arXiv  Detail & Related papers  (2021-06-23T16:04:25Z)
• Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
  We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
  arXiv  Detail & Related papers  (2020-10-18T16:55:25Z)
• A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
  Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem. We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
  arXiv  Detail & Related papers  (2020-10-05T04:57:18Z)
• Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case [93.37576644429578]
  Graph neural networks (GNNs) have made great progress recently on learning from graph-structured data in practice. We provide a theoretically-grounded generalizability analysis of GNNs with one hidden layer for both regression and binary classification problems.
  arXiv  Detail & Related papers  (2020-06-25T00:45:52Z)
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks [3.1510406584101776]
  Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. In this paper, we show that GNNs can in fact be naturally explained using higher-order expansions. We extract practically relevant insights on sentiment analysis of text data, structure-property relationships in quantum chemistry, and image classification.
  arXiv  Detail & Related papers  (2020-06-05T17:59:14Z)
• XGNN: Towards Model-Level Explanations of Graph Neural Networks [113.51160387804484]
  Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information. GNNs are mostly treated as black-boxes and lack human intelligible explanations. We propose a novel approach, known as XGNN, to interpret GNNs at the model-level.
  arXiv  Detail & Related papers  (2020-06-03T23:52:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.