Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint

• URL: http://arxiv.org/abs/2406.04612v2
• Date: Fri, 20 Dec 2024 11:17:45 GMT
• Title: Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint
• Authors: Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin,
• Abstract summary: We propose GATT, edge attribution calculation method for self-attention MPNNs based on the computation tree.<n>Despite its simplicity, we empirically demonstrate the effectiveness of GATT in three aspects of model explanation.
• Score: 11.459893079664578
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such attention-based MPNNs (Att-GNNs) have also been used as a baseline for multiple studies on explainable AI (XAI) since attention has steadily been seen as natural model interpretations, while being a viewpoint that has already been popularized in other domains (e.g., natural language processing and computer vision). However, existing studies often use naive calculations to derive attribution scores from attention, undermining the potential of attention as interpretations for Att-GNNs. In our study, we aim to fill the gap between the widespread usage of Att-GNNs and their potential explainability via attention. To this end, we propose GATT, edge attribution calculation method for self-attention MPNNs based on the computation tree, a rooted tree that reflects the computation process of the underlying model. Despite its simplicity, we empirically demonstrate the effectiveness of GATT in three aspects of model explanation: faithfulness, explanation accuracy, and case studies by using both synthetic and real-world benchmark datasets. In all cases, the results demonstrate that GATT greatly improves edge attribution scores, especially compared to the previous naive approach. Our code is available at https://github.com/jordan7186/GAtt.

Related papers

• Towards Fair Graph Representation Learning in Social Networks [20.823461673845756]
  We introduce constraints for fair representation learning based on three principles: sufficiency, independence, and separation. We theoretically demonstrate that our EAGNN method can effectively achieve group fairness.
  arXiv  Detail & Related papers  (2024-10-15T10:57:02Z)
• PROXI: Challenging the GNNs for Link Prediction [3.8233569758620063]
  We introduce PROXI, which leverages proximity information of node pairs in both graph and attribute spaces. Standard machine learning (ML) models perform competitively, even outperforming cutting-edge GNN models. We show that augmenting traditional GNNs with PROXI significantly boosts their link prediction performance.
  arXiv  Detail & Related papers  (2024-10-02T17:57:38Z)
• GraphGI:A GNN Explanation Method using Game Interaction [5.149896909638598]
  Graph Neural Networks (GNNs) have garnered significant attention and have been extensively utilized across various domains. Current graph explanation techniques focus on identifying key nodes or edges, attributing the critical data features that drive model predictions. We propose a novel explanatory method GraphGI, which identifies the coalition with the highest interaction strength and presents it as an explanatory subgraph.
  arXiv  Detail & Related papers  (2024-09-24T03:24:31Z)
• Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability [0.9499648210774584]
  We show the emergence of Massive Activations (MAs) within attention layers in edge-featured Graph Neural Networks (GNNs) Our study assesses various edge-featured attention-based GNN models using benchmark datasets, including ZINC, TOX21, and PROTEINS.
  arXiv  Detail & Related papers  (2024-09-05T12:19:07Z)
• Kolmogorov-Arnold Graph Neural Networks [2.4005219869876453]
  Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability. We propose the Graph Kolmogorov-Arnold Network (GKAN) to enhance both accuracy and interpretability.
  arXiv  Detail & Related papers  (2024-06-26T13:54:59Z)
• Are GATs Out of Balance? [73.2500577189791]
  We study the Graph Attention Network (GAT) in which a node's neighborhood aggregation is weighted by parameterized attention coefficients. Our main theorem serves as a stepping stone to studying the learning dynamics of positive homogeneous models with attention mechanisms.
  arXiv  Detail & Related papers  (2023-10-11T06:53:05Z)
• Information Flow in Graph Neural Networks: A Clinical Triage Use Case [49.86931948849343]
  Graph Neural Networks (GNNs) have gained popularity in healthcare and other domains due to their ability to process multi-modal and multi-relational graphs. We investigate how the flow of embedding information within GNNs affects the prediction of links in Knowledge Graphs (KGs) Our results demonstrate that incorporating domain knowledge into the GNN connectivity leads to better performance than using the same connectivity as the KG or allowing unconstrained embedding propagation.
  arXiv  Detail & Related papers  (2023-09-12T09:18:12Z)
• Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models [9.260186030255081]
  We propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Our work extends existing attention-based graph explainability methods by analysing the divergence in the attention distributions in relation to semantically sorted feature sets. We apply our methodology on a lidar pointcloud estimation model successfully identifying key semantic classes that contribute to enhanced performance.
  arXiv  Detail & Related papers  (2023-08-08T12:34:32Z)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• FairGAT: Fairness-aware Graph Attention Networks [9.492903649862761]
  Graph attention networks (GATs) have become one of the most widely utilized neural network structures for graph-based tasks. The influence of the attention design in GATs on algorithmic bias has not been investigated. A novel algorithm, FairGAT, that leverages a fairness-aware attention design is developed.
  arXiv  Detail & Related papers  (2023-03-26T00:10:20Z)
• Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs [71.93227401463199]
  This paper pinpoints the major source of GNNs' performance gain to their intrinsic capability, by introducing an intermediate model class dubbed as P(ropagational)MLP. We observe that PMLPs consistently perform on par with (or even exceed) their GNN counterparts, while being much more efficient in training.
  arXiv  Detail & Related papers  (2022-12-18T08:17:32Z)
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs [51.33152272781324]
  Graph Neural Networks (GNNs) are proposed without considering the distribution shifts between training and testing graphs. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. We propose a general causal representation framework, called StableGNN, to eliminate the impact of spurious correlations.
  arXiv  Detail & Related papers  (2021-11-20T18:57:18Z)
• Boundary Attributions Provide Normal (Vector) Explanations [27.20904776964045]
  Boundary Attribution (BA) is a new explanation method to address this question. BA involves computing normal vectors of the local decision boundaries for the target input. We prove two theorems for ReLU networks: BA of randomized smoothed networks or robustly trained networks is much closer to non-boundary attribution methods than that in standard networks.
  arXiv  Detail & Related papers  (2021-03-20T22:36:39Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  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.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)
• Graph Backdoor [53.70971502299977]
  We present GTA, the first backdoor attack on graph neural networks (GNNs) GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features. It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
  arXiv  Detail & Related papers  (2020-06-21T19:45:30Z)
• Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification [70.50751397870972]
  FastGAT is a method to make attention based GNNs lightweight by using spectral sparsification to generate an optimal pruning of the input graph. We experimentally evaluate FastGAT on several large real world graph datasets for node classification tasks.
  arXiv  Detail & Related papers  (2020-06-15T22:07:54Z)
• Attention improves concentration when learning node embeddings [1.2233362977312945]
  Given nodes labelled with search query text, we want to predict links to related queries that share products. Experiments with a range of deep neural architectures show that simple feedforward networks with an attention mechanism perform best for learning embeddings. We propose an analytically tractable model of query generation, AttEST, that views both products and the query text as vectors embedded in a latent space.
  arXiv  Detail & Related papers  (2020-06-11T21:21:12Z)
• Spectral Graph Attention Network with Fast Eigen-approximation [103.93113062682633]
  Spectral Graph Attention Network (SpGAT) learns representations for different frequency components regarding weighted filters and graph wavelets bases. Fast approximation variant SpGAT-Cheby is proposed to reduce the computational cost brought by the eigen-decomposition. We thoroughly evaluate the performance of SpGAT and SpGAT-Cheby in semi-supervised node classification tasks.
  arXiv  Detail & Related papers  (2020-03-16T21:49:34Z)
• Node Masking: Making Graph Neural Networks Generalize and Scale Better [71.51292866945471]
  Graph Neural Networks (GNNs) have received a lot of interest in the recent times. In this paper, we utilize some theoretical tools to better visualize the operations performed by state of the art spatial GNNs. We introduce a simple concept, Node Masking, that allows them to generalize and scale better.
  arXiv  Detail & Related papers  (2020-01-17T06:26:40Z)

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.